@synsci/cli-darwin-x64-baseline 1.1.71 → 1.1.73

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (339) hide show
  1. package/bin/skills/citation-management/SKILL.md +1109 -0
  2. package/bin/skills/citation-management/assets/bibtex_template.bib +264 -0
  3. package/bin/skills/citation-management/assets/citation_checklist.md +386 -0
  4. package/bin/skills/citation-management/references/bibtex_formatting.md +908 -0
  5. package/bin/skills/citation-management/references/citation_validation.md +794 -0
  6. package/bin/skills/citation-management/references/google_scholar_search.md +725 -0
  7. package/bin/skills/citation-management/references/metadata_extraction.md +870 -0
  8. package/bin/skills/citation-management/references/pubmed_search.md +839 -0
  9. package/bin/skills/citation-management/scripts/doi_to_bibtex.py +182 -0
  10. package/bin/skills/citation-management/scripts/extract_metadata.py +570 -0
  11. package/bin/skills/citation-management/scripts/format_bibtex.py +349 -0
  12. package/bin/skills/citation-management/scripts/search_google_scholar.py +251 -0
  13. package/bin/skills/citation-management/scripts/search_pubmed.py +348 -0
  14. package/bin/skills/citation-management/scripts/validate_citations.py +494 -0
  15. package/bin/skills/clinical-decision-support/README.md +129 -0
  16. package/bin/skills/clinical-decision-support/SKILL.md +506 -0
  17. package/bin/skills/clinical-decision-support/assets/biomarker_report_template.tex +380 -0
  18. package/bin/skills/clinical-decision-support/assets/clinical_pathway_template.tex +222 -0
  19. package/bin/skills/clinical-decision-support/assets/cohort_analysis_template.tex +359 -0
  20. package/bin/skills/clinical-decision-support/assets/color_schemes.tex +149 -0
  21. package/bin/skills/clinical-decision-support/assets/example_gbm_cohort.md +208 -0
  22. package/bin/skills/clinical-decision-support/assets/recommendation_strength_guide.md +328 -0
  23. package/bin/skills/clinical-decision-support/assets/treatment_recommendation_template.tex +529 -0
  24. package/bin/skills/clinical-decision-support/references/biomarker_classification.md +719 -0
  25. package/bin/skills/clinical-decision-support/references/clinical_decision_algorithms.md +604 -0
  26. package/bin/skills/clinical-decision-support/references/evidence_synthesis.md +840 -0
  27. package/bin/skills/clinical-decision-support/references/outcome_analysis.md +640 -0
  28. package/bin/skills/clinical-decision-support/references/patient_cohort_analysis.md +427 -0
  29. package/bin/skills/clinical-decision-support/references/treatment_recommendations.md +521 -0
  30. package/bin/skills/clinical-decision-support/scripts/biomarker_classifier.py +383 -0
  31. package/bin/skills/clinical-decision-support/scripts/build_decision_tree.py +417 -0
  32. package/bin/skills/clinical-decision-support/scripts/create_cohort_tables.py +509 -0
  33. package/bin/skills/clinical-decision-support/scripts/generate_survival_analysis.py +441 -0
  34. package/bin/skills/clinical-decision-support/scripts/validate_cds_document.py +326 -0
  35. package/bin/skills/clinical-reports/IMPLEMENTATION_SUMMARY.md +641 -0
  36. package/bin/skills/clinical-reports/README.md +236 -0
  37. package/bin/skills/clinical-reports/SKILL.md +1127 -0
  38. package/bin/skills/clinical-reports/assets/case_report_template.md +352 -0
  39. package/bin/skills/clinical-reports/assets/clinical_trial_csr_template.md +353 -0
  40. package/bin/skills/clinical-reports/assets/clinical_trial_sae_template.md +359 -0
  41. package/bin/skills/clinical-reports/assets/consult_note_template.md +305 -0
  42. package/bin/skills/clinical-reports/assets/discharge_summary_template.md +453 -0
  43. package/bin/skills/clinical-reports/assets/hipaa_compliance_checklist.md +395 -0
  44. package/bin/skills/clinical-reports/assets/history_physical_template.md +305 -0
  45. package/bin/skills/clinical-reports/assets/lab_report_template.md +309 -0
  46. package/bin/skills/clinical-reports/assets/pathology_report_template.md +249 -0
  47. package/bin/skills/clinical-reports/assets/quality_checklist.md +338 -0
  48. package/bin/skills/clinical-reports/assets/radiology_report_template.md +318 -0
  49. package/bin/skills/clinical-reports/assets/soap_note_template.md +253 -0
  50. package/bin/skills/clinical-reports/references/case_report_guidelines.md +570 -0
  51. package/bin/skills/clinical-reports/references/clinical_trial_reporting.md +693 -0
  52. package/bin/skills/clinical-reports/references/data_presentation.md +530 -0
  53. package/bin/skills/clinical-reports/references/diagnostic_reports_standards.md +629 -0
  54. package/bin/skills/clinical-reports/references/medical_terminology.md +588 -0
  55. package/bin/skills/clinical-reports/references/patient_documentation.md +744 -0
  56. package/bin/skills/clinical-reports/references/peer_review_standards.md +585 -0
  57. package/bin/skills/clinical-reports/references/regulatory_compliance.md +577 -0
  58. package/bin/skills/clinical-reports/scripts/check_deidentification.py +332 -0
  59. package/bin/skills/clinical-reports/scripts/compliance_checker.py +78 -0
  60. package/bin/skills/clinical-reports/scripts/extract_clinical_data.py +97 -0
  61. package/bin/skills/clinical-reports/scripts/format_adverse_events.py +97 -0
  62. package/bin/skills/clinical-reports/scripts/generate_report_template.py +149 -0
  63. package/bin/skills/clinical-reports/scripts/terminology_validator.py +126 -0
  64. package/bin/skills/clinical-reports/scripts/validate_case_report.py +323 -0
  65. package/bin/skills/clinical-reports/scripts/validate_trial_report.py +88 -0
  66. package/bin/skills/fireworks-ai/SKILL.md +665 -0
  67. package/bin/skills/generate-image/SKILL.md +178 -0
  68. package/bin/skills/generate-image/scripts/generate_image.py +254 -0
  69. package/bin/skills/groq/SKILL.md +347 -0
  70. package/bin/skills/hypothesis-generation/SKILL.md +293 -0
  71. package/bin/skills/hypothesis-generation/assets/FORMATTING_GUIDE.md +672 -0
  72. package/bin/skills/hypothesis-generation/assets/hypothesis_generation.sty +307 -0
  73. package/bin/skills/hypothesis-generation/assets/hypothesis_report_template.tex +572 -0
  74. package/bin/skills/hypothesis-generation/references/experimental_design_patterns.md +329 -0
  75. package/bin/skills/hypothesis-generation/references/hypothesis_quality_criteria.md +198 -0
  76. package/bin/skills/hypothesis-generation/references/literature_search_strategies.md +622 -0
  77. package/bin/skills/latex-posters/README.md +417 -0
  78. package/bin/skills/latex-posters/SKILL.md +1602 -0
  79. package/bin/skills/latex-posters/assets/baposter_template.tex +257 -0
  80. package/bin/skills/latex-posters/assets/beamerposter_template.tex +244 -0
  81. package/bin/skills/latex-posters/assets/poster_quality_checklist.md +358 -0
  82. package/bin/skills/latex-posters/assets/tikzposter_template.tex +251 -0
  83. package/bin/skills/latex-posters/references/latex_poster_packages.md +745 -0
  84. package/bin/skills/latex-posters/references/poster_content_guide.md +748 -0
  85. package/bin/skills/latex-posters/references/poster_design_principles.md +806 -0
  86. package/bin/skills/latex-posters/references/poster_layout_design.md +900 -0
  87. package/bin/skills/latex-posters/scripts/review_poster.sh +214 -0
  88. package/bin/skills/literature-review/SKILL.md +641 -0
  89. package/bin/skills/literature-review/assets/review_template.md +412 -0
  90. package/bin/skills/literature-review/references/citation_styles.md +166 -0
  91. package/bin/skills/literature-review/references/database_strategies.md +455 -0
  92. package/bin/skills/literature-review/scripts/generate_pdf.py +184 -0
  93. package/bin/skills/literature-review/scripts/search_databases.py +310 -0
  94. package/bin/skills/literature-review/scripts/verify_citations.py +218 -0
  95. package/bin/skills/market-research-reports/SKILL.md +904 -0
  96. package/bin/skills/market-research-reports/assets/FORMATTING_GUIDE.md +428 -0
  97. package/bin/skills/market-research-reports/assets/market_report_template.tex +1380 -0
  98. package/bin/skills/market-research-reports/assets/market_research.sty +564 -0
  99. package/bin/skills/market-research-reports/references/data_analysis_patterns.md +548 -0
  100. package/bin/skills/market-research-reports/references/report_structure_guide.md +999 -0
  101. package/bin/skills/market-research-reports/references/visual_generation_guide.md +1077 -0
  102. package/bin/skills/market-research-reports/scripts/generate_market_visuals.py +472 -0
  103. package/bin/skills/markitdown/INSTALLATION_GUIDE.md +318 -0
  104. package/bin/skills/markitdown/LICENSE.txt +22 -0
  105. package/bin/skills/markitdown/OPENROUTER_INTEGRATION.md +359 -0
  106. package/bin/skills/markitdown/QUICK_REFERENCE.md +309 -0
  107. package/bin/skills/markitdown/README.md +184 -0
  108. package/bin/skills/markitdown/SKILL.md +486 -0
  109. package/bin/skills/markitdown/SKILL_SUMMARY.md +307 -0
  110. package/bin/skills/markitdown/assets/example_usage.md +463 -0
  111. package/bin/skills/markitdown/references/api_reference.md +399 -0
  112. package/bin/skills/markitdown/references/file_formats.md +542 -0
  113. package/bin/skills/markitdown/scripts/batch_convert.py +195 -0
  114. package/bin/skills/markitdown/scripts/convert_literature.py +262 -0
  115. package/bin/skills/markitdown/scripts/convert_with_ai.py +224 -0
  116. package/bin/skills/ml-paper-writing/SKILL.md +937 -0
  117. package/bin/skills/ml-paper-writing/references/checklists.md +361 -0
  118. package/bin/skills/ml-paper-writing/references/citation-workflow.md +562 -0
  119. package/bin/skills/ml-paper-writing/references/reviewer-guidelines.md +367 -0
  120. package/bin/skills/ml-paper-writing/references/sources.md +159 -0
  121. package/bin/skills/ml-paper-writing/references/writing-guide.md +476 -0
  122. package/bin/skills/ml-paper-writing/templates/README.md +251 -0
  123. package/bin/skills/ml-paper-writing/templates/aaai2026/README.md +534 -0
  124. package/bin/skills/ml-paper-writing/templates/aaai2026/aaai2026-unified-supp.tex +144 -0
  125. package/bin/skills/ml-paper-writing/templates/aaai2026/aaai2026-unified-template.tex +952 -0
  126. package/bin/skills/ml-paper-writing/templates/aaai2026/aaai2026.bib +111 -0
  127. package/bin/skills/ml-paper-writing/templates/aaai2026/aaai2026.bst +1493 -0
  128. package/bin/skills/ml-paper-writing/templates/aaai2026/aaai2026.sty +315 -0
  129. package/bin/skills/ml-paper-writing/templates/acl/README.md +50 -0
  130. package/bin/skills/ml-paper-writing/templates/acl/acl.sty +312 -0
  131. package/bin/skills/ml-paper-writing/templates/acl/acl_latex.tex +377 -0
  132. package/bin/skills/ml-paper-writing/templates/acl/acl_lualatex.tex +101 -0
  133. package/bin/skills/ml-paper-writing/templates/acl/acl_natbib.bst +1940 -0
  134. package/bin/skills/ml-paper-writing/templates/acl/anthology.bib.txt +26 -0
  135. package/bin/skills/ml-paper-writing/templates/acl/custom.bib +70 -0
  136. package/bin/skills/ml-paper-writing/templates/acl/formatting.md +326 -0
  137. package/bin/skills/ml-paper-writing/templates/colm2025/README.md +3 -0
  138. package/bin/skills/ml-paper-writing/templates/colm2025/colm2025_conference.bib +11 -0
  139. package/bin/skills/ml-paper-writing/templates/colm2025/colm2025_conference.bst +1440 -0
  140. package/bin/skills/ml-paper-writing/templates/colm2025/colm2025_conference.pdf +0 -0
  141. package/bin/skills/ml-paper-writing/templates/colm2025/colm2025_conference.sty +218 -0
  142. package/bin/skills/ml-paper-writing/templates/colm2025/colm2025_conference.tex +305 -0
  143. package/bin/skills/ml-paper-writing/templates/colm2025/fancyhdr.sty +485 -0
  144. package/bin/skills/ml-paper-writing/templates/colm2025/math_commands.tex +508 -0
  145. package/bin/skills/ml-paper-writing/templates/colm2025/natbib.sty +1246 -0
  146. package/bin/skills/ml-paper-writing/templates/iclr2026/fancyhdr.sty +485 -0
  147. package/bin/skills/ml-paper-writing/templates/iclr2026/iclr2026_conference.bib +24 -0
  148. package/bin/skills/ml-paper-writing/templates/iclr2026/iclr2026_conference.bst +1440 -0
  149. package/bin/skills/ml-paper-writing/templates/iclr2026/iclr2026_conference.pdf +0 -0
  150. package/bin/skills/ml-paper-writing/templates/iclr2026/iclr2026_conference.sty +246 -0
  151. package/bin/skills/ml-paper-writing/templates/iclr2026/iclr2026_conference.tex +414 -0
  152. package/bin/skills/ml-paper-writing/templates/iclr2026/math_commands.tex +508 -0
  153. package/bin/skills/ml-paper-writing/templates/iclr2026/natbib.sty +1246 -0
  154. package/bin/skills/ml-paper-writing/templates/icml2026/algorithm.sty +79 -0
  155. package/bin/skills/ml-paper-writing/templates/icml2026/algorithmic.sty +201 -0
  156. package/bin/skills/ml-paper-writing/templates/icml2026/example_paper.bib +75 -0
  157. package/bin/skills/ml-paper-writing/templates/icml2026/example_paper.pdf +0 -0
  158. package/bin/skills/ml-paper-writing/templates/icml2026/example_paper.tex +662 -0
  159. package/bin/skills/ml-paper-writing/templates/icml2026/fancyhdr.sty +864 -0
  160. package/bin/skills/ml-paper-writing/templates/icml2026/icml2026.bst +1443 -0
  161. package/bin/skills/ml-paper-writing/templates/icml2026/icml2026.sty +767 -0
  162. package/bin/skills/ml-paper-writing/templates/icml2026/icml_numpapers.pdf +0 -0
  163. package/bin/skills/ml-paper-writing/templates/neurips2025/Makefile +36 -0
  164. package/bin/skills/ml-paper-writing/templates/neurips2025/extra_pkgs.tex +53 -0
  165. package/bin/skills/ml-paper-writing/templates/neurips2025/main.tex +38 -0
  166. package/bin/skills/ml-paper-writing/templates/neurips2025/neurips.sty +382 -0
  167. package/bin/skills/paper-2-web/SKILL.md +491 -0
  168. package/bin/skills/paper-2-web/references/installation.md +141 -0
  169. package/bin/skills/paper-2-web/references/paper2poster.md +346 -0
  170. package/bin/skills/paper-2-web/references/paper2video.md +305 -0
  171. package/bin/skills/paper-2-web/references/paper2web.md +187 -0
  172. package/bin/skills/paper-2-web/references/usage_examples.md +436 -0
  173. package/bin/skills/peer-review/SKILL.md +702 -0
  174. package/bin/skills/peer-review/references/calibration_guidelines.md +196 -0
  175. package/bin/skills/peer-review/references/common_issues.md +552 -0
  176. package/bin/skills/peer-review/references/paper_mechanics.md +269 -0
  177. package/bin/skills/peer-review/references/reporting_standards.md +290 -0
  178. package/bin/skills/peer-review/references/scoring_rubric.md +239 -0
  179. package/bin/skills/pptx-posters/SKILL.md +410 -0
  180. package/bin/skills/pptx-posters/assets/poster_html_template.html +257 -0
  181. package/bin/skills/pptx-posters/assets/poster_quality_checklist.md +358 -0
  182. package/bin/skills/pptx-posters/references/poster_content_guide.md +748 -0
  183. package/bin/skills/pptx-posters/references/poster_design_principles.md +806 -0
  184. package/bin/skills/pptx-posters/references/poster_layout_design.md +900 -0
  185. package/bin/skills/research-grants/README.md +285 -0
  186. package/bin/skills/research-grants/SKILL.md +938 -0
  187. package/bin/skills/research-grants/assets/budget_justification_template.md +453 -0
  188. package/bin/skills/research-grants/assets/nih_specific_aims_template.md +166 -0
  189. package/bin/skills/research-grants/assets/nsf_project_summary_template.md +92 -0
  190. package/bin/skills/research-grants/references/broader_impacts.md +392 -0
  191. package/bin/skills/research-grants/references/darpa_guidelines.md +636 -0
  192. package/bin/skills/research-grants/references/doe_guidelines.md +586 -0
  193. package/bin/skills/research-grants/references/nih_guidelines.md +851 -0
  194. package/bin/skills/research-grants/references/nsf_guidelines.md +570 -0
  195. package/bin/skills/research-grants/references/specific_aims_guide.md +458 -0
  196. package/bin/skills/research-lookup/README.md +156 -0
  197. package/bin/skills/research-lookup/SKILL.md +606 -0
  198. package/bin/skills/research-lookup/examples.py +174 -0
  199. package/bin/skills/research-lookup/lookup.py +187 -0
  200. package/bin/skills/research-lookup/research_lookup.py +483 -0
  201. package/bin/skills/research-lookup/scripts/research_lookup.py +483 -0
  202. package/bin/skills/scholar-evaluation/SKILL.md +289 -0
  203. package/bin/skills/scholar-evaluation/references/evaluation_framework.md +663 -0
  204. package/bin/skills/scholar-evaluation/scripts/calculate_scores.py +366 -0
  205. package/bin/skills/scientific-critical-thinking/SKILL.md +566 -0
  206. package/bin/skills/scientific-critical-thinking/references/common_biases.md +364 -0
  207. package/bin/skills/scientific-critical-thinking/references/evidence_hierarchy.md +484 -0
  208. package/bin/skills/scientific-critical-thinking/references/experimental_design.md +496 -0
  209. package/bin/skills/scientific-critical-thinking/references/logical_fallacies.md +478 -0
  210. package/bin/skills/scientific-critical-thinking/references/scientific_method.md +169 -0
  211. package/bin/skills/scientific-critical-thinking/references/statistical_pitfalls.md +506 -0
  212. package/bin/skills/scientific-schematics/QUICK_REFERENCE.md +207 -0
  213. package/bin/skills/scientific-schematics/README.md +327 -0
  214. package/bin/skills/scientific-schematics/SKILL.md +615 -0
  215. package/bin/skills/scientific-schematics/example_usage.sh +89 -0
  216. package/bin/skills/scientific-schematics/references/best_practices.md +559 -0
  217. package/bin/skills/scientific-schematics/scripts/generate_schematic.py +135 -0
  218. package/bin/skills/scientific-schematics/scripts/generate_schematic_ai.py +807 -0
  219. package/bin/skills/scientific-schematics/test_ai_generation.py +243 -0
  220. package/bin/skills/scientific-slides/SKILL.md +942 -0
  221. package/bin/skills/scientific-slides/assets/timing_guidelines.md +597 -0
  222. package/bin/skills/scientific-slides/references/data_visualization_slides.md +708 -0
  223. package/bin/skills/scientific-slides/references/presentation_structure.md +642 -0
  224. package/bin/skills/scientific-slides/references/slide_design_principles.md +849 -0
  225. package/bin/skills/scientific-slides/references/talk_types_guide.md +687 -0
  226. package/bin/skills/scientific-slides/references/visual_review_workflow.md +775 -0
  227. package/bin/skills/scientific-slides/scripts/generate_slide_image.py +143 -0
  228. package/bin/skills/scientific-slides/scripts/generate_slide_image_ai.py +748 -0
  229. package/bin/skills/scientific-slides/scripts/pdf_to_images.py +201 -0
  230. package/bin/skills/scientific-slides/scripts/slides_to_pdf.py +220 -0
  231. package/bin/skills/scientific-slides/scripts/validate_presentation.py +367 -0
  232. package/bin/skills/scientific-writing/SKILL.md +714 -0
  233. package/bin/skills/scientific-writing/assets/REPORT_FORMATTING_GUIDE.md +574 -0
  234. package/bin/skills/scientific-writing/assets/scientific_report.sty +606 -0
  235. package/bin/skills/scientific-writing/assets/scientific_report_template.tex +449 -0
  236. package/bin/skills/scientific-writing/references/citation_styles.md +720 -0
  237. package/bin/skills/scientific-writing/references/figures_tables.md +806 -0
  238. package/bin/skills/scientific-writing/references/imrad_structure.md +686 -0
  239. package/bin/skills/scientific-writing/references/professional_report_formatting.md +664 -0
  240. package/bin/skills/scientific-writing/references/reporting_guidelines.md +748 -0
  241. package/bin/skills/scientific-writing/references/writing_principles.md +824 -0
  242. package/bin/skills/tinker/SKILL.md +2 -3
  243. package/bin/skills/together-ai/SKILL.md +722 -0
  244. package/bin/skills/treatment-plans/README.md +488 -0
  245. package/bin/skills/treatment-plans/SKILL.md +1579 -0
  246. package/bin/skills/treatment-plans/assets/STYLING_QUICK_REFERENCE.md +185 -0
  247. package/bin/skills/treatment-plans/assets/chronic_disease_management_plan.tex +665 -0
  248. package/bin/skills/treatment-plans/assets/general_medical_treatment_plan.tex +547 -0
  249. package/bin/skills/treatment-plans/assets/medical_treatment_plan.sty +222 -0
  250. package/bin/skills/treatment-plans/assets/mental_health_treatment_plan.tex +774 -0
  251. package/bin/skills/treatment-plans/assets/one_page_treatment_plan.tex +193 -0
  252. package/bin/skills/treatment-plans/assets/pain_management_plan.tex +799 -0
  253. package/bin/skills/treatment-plans/assets/perioperative_care_plan.tex +753 -0
  254. package/bin/skills/treatment-plans/assets/quality_checklist.md +471 -0
  255. package/bin/skills/treatment-plans/assets/rehabilitation_treatment_plan.tex +756 -0
  256. package/bin/skills/treatment-plans/references/goal_setting_frameworks.md +411 -0
  257. package/bin/skills/treatment-plans/references/intervention_guidelines.md +507 -0
  258. package/bin/skills/treatment-plans/references/regulatory_compliance.md +476 -0
  259. package/bin/skills/treatment-plans/references/specialty_specific_guidelines.md +655 -0
  260. package/bin/skills/treatment-plans/references/treatment_plan_standards.md +485 -0
  261. package/bin/skills/treatment-plans/scripts/check_completeness.py +322 -0
  262. package/bin/skills/treatment-plans/scripts/generate_template.py +233 -0
  263. package/bin/skills/treatment-plans/scripts/timeline_generator.py +385 -0
  264. package/bin/skills/treatment-plans/scripts/validate_treatment_plan.py +369 -0
  265. package/bin/skills/unsloth/SKILL.md +565 -47
  266. package/bin/skills/unsloth/docs/advanced-rl.md +222 -0
  267. package/bin/skills/unsloth/docs/chat-templates.md +141 -0
  268. package/bin/skills/unsloth/docs/datasets.md +489 -0
  269. package/bin/skills/unsloth/docs/docker-extended.md +99 -0
  270. package/bin/skills/unsloth/docs/dynamic-ggufs-2.0.md +116 -0
  271. package/bin/skills/unsloth/docs/dynamic-ggufs-aider.md +118 -0
  272. package/bin/skills/unsloth/docs/faq.md +91 -0
  273. package/bin/skills/unsloth/docs/fp16-vs-bf16.md +61 -0
  274. package/bin/skills/unsloth/docs/fp8-rl.md +224 -0
  275. package/bin/skills/unsloth/docs/glm-4.7-flash.md +997 -0
  276. package/bin/skills/unsloth/docs/inference-deployment-overview.md +17 -0
  277. package/bin/skills/unsloth/docs/inference.md +27 -0
  278. package/bin/skills/unsloth/docs/installation-docker.md +155 -0
  279. package/bin/skills/unsloth/docs/installation-pip.md +148 -0
  280. package/bin/skills/unsloth/docs/kernels-packing.md +190 -0
  281. package/bin/skills/unsloth/docs/kimi-k2.5.md +634 -0
  282. package/bin/skills/unsloth/docs/lm-studio.md +235 -0
  283. package/bin/skills/unsloth/docs/lora-hot-swapping.md +75 -0
  284. package/bin/skills/unsloth/docs/lora-hyperparameters.md +363 -0
  285. package/bin/skills/unsloth/docs/memory-efficient-rl.md +267 -0
  286. package/bin/skills/unsloth/docs/model-selection.md +70 -0
  287. package/bin/skills/unsloth/docs/models.md +532 -0
  288. package/bin/skills/unsloth/docs/multi-gpu-ddp.md +90 -0
  289. package/bin/skills/unsloth/docs/notebooks.md +223 -0
  290. package/bin/skills/unsloth/docs/overview.md +110 -0
  291. package/bin/skills/unsloth/docs/qwen3-coder-next-extended.md +900 -0
  292. package/bin/skills/unsloth/docs/qwen3-coder-next.md +900 -0
  293. package/bin/skills/unsloth/docs/requirements.md +45 -0
  294. package/bin/skills/unsloth/docs/reward-hacking.md +25 -0
  295. package/bin/skills/unsloth/docs/saving-to-gguf.md +138 -0
  296. package/bin/skills/unsloth/docs/saving-to-ollama.md +46 -0
  297. package/bin/skills/unsloth/docs/sglang-guide.md +278 -0
  298. package/bin/skills/unsloth/docs/speculative-decoding.md +70 -0
  299. package/bin/skills/unsloth/docs/tool-calling.md +334 -0
  300. package/bin/skills/unsloth/docs/troubleshooting-faq.md +204 -0
  301. package/bin/skills/unsloth/docs/troubleshooting-inference.md +26 -0
  302. package/bin/skills/unsloth/docs/tts-fine-tuning.md +149 -0
  303. package/bin/skills/unsloth/docs/tutorial-grpo.md +273 -0
  304. package/bin/skills/unsloth/docs/tutorial-llama3-ollama.md +356 -0
  305. package/bin/skills/unsloth/docs/vision-fine-tuning.md +135 -0
  306. package/bin/skills/unsloth/docs/vision-rl.md +170 -0
  307. package/bin/skills/unsloth/docs/vllm-engine-arguments.md +43 -0
  308. package/bin/skills/unsloth/docs/vllm-guide.md +98 -0
  309. package/bin/skills/venue-templates/SKILL.md +686 -0
  310. package/bin/skills/venue-templates/assets/examples/cell_summary_example.md +247 -0
  311. package/bin/skills/venue-templates/assets/examples/medical_structured_abstract.md +313 -0
  312. package/bin/skills/venue-templates/assets/examples/nature_abstract_examples.md +213 -0
  313. package/bin/skills/venue-templates/assets/examples/neurips_introduction_example.md +245 -0
  314. package/bin/skills/venue-templates/assets/grants/nih_specific_aims.tex +235 -0
  315. package/bin/skills/venue-templates/assets/grants/nsf_proposal_template.tex +375 -0
  316. package/bin/skills/venue-templates/assets/journals/nature_article.tex +171 -0
  317. package/bin/skills/venue-templates/assets/journals/neurips_article.tex +283 -0
  318. package/bin/skills/venue-templates/assets/journals/plos_one.tex +317 -0
  319. package/bin/skills/venue-templates/assets/posters/beamerposter_academic.tex +311 -0
  320. package/bin/skills/venue-templates/references/cell_press_style.md +483 -0
  321. package/bin/skills/venue-templates/references/conferences_formatting.md +564 -0
  322. package/bin/skills/venue-templates/references/cs_conference_style.md +463 -0
  323. package/bin/skills/venue-templates/references/grants_requirements.md +787 -0
  324. package/bin/skills/venue-templates/references/journals_formatting.md +486 -0
  325. package/bin/skills/venue-templates/references/medical_journal_styles.md +535 -0
  326. package/bin/skills/venue-templates/references/ml_conference_style.md +556 -0
  327. package/bin/skills/venue-templates/references/nature_science_style.md +405 -0
  328. package/bin/skills/venue-templates/references/posters_guidelines.md +628 -0
  329. package/bin/skills/venue-templates/references/reviewer_expectations.md +417 -0
  330. package/bin/skills/venue-templates/references/venue_writing_styles.md +321 -0
  331. package/bin/skills/venue-templates/scripts/customize_template.py +195 -0
  332. package/bin/skills/venue-templates/scripts/query_template.py +266 -0
  333. package/bin/skills/venue-templates/scripts/validate_format.py +250 -0
  334. package/bin/synsc +0 -0
  335. package/package.json +1 -1
  336. package/bin/skills/unsloth/references/index.md +0 -7
  337. package/bin/skills/unsloth/references/llms-full.md +0 -16799
  338. package/bin/skills/unsloth/references/llms-txt.md +0 -12044
  339. package/bin/skills/unsloth/references/llms.md +0 -82
package/bin/skills/unsloth/docs/models.md ADDED
@@ -0,0 +1,532 @@
1
+ # Unsloth Model Catalog
2
+
3
+ Unsloth model catalog for all our [Dynamic](https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs) GGUF, 4-bit, 16-bit models on Hugging Face.
4
+
5
+ {% tabs %}
6
+ {% tab title="• GGUF + 4-bit" %} <a href="#deepseek-models" class="button secondary">DeepSeek</a><a href="#llama-models" class="button secondary">Llama</a><a href="#gemma-models" class="button secondary">Gemma</a><a href="#qwen-models" class="button secondary">Qwen</a><a href="#mistral-models" class="button secondary">Mistral</a><a href="#phi-models" class="button secondary">Phi</a>
7
+
8
+ **GGUFs** let you run models in tools like Ollama, Open WebUI, and llama.cpp.\
9
+ **Instruct (4-bit)** safetensors can be used for inference or fine-tuning.
10
+
11
+ #### New & recommended models:
12
+
13
+ | Model | Variant | GGUF | Instruct (4-bit) |
14
+ | ---------------------------------------------------------------------------------------------- | ------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
15
+ | **GLM** | [4.7-Flash](https://unsloth.ai/docs/models/glm-4.7-flash) | [link](https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF) | — |
16
+ | | [5](https://unsloth.ai/docs/models/glm-5) | [link](https://huggingface.co/unsloth/GLM-5-GGUF) | — |
17
+ | **Qwen3** | [Coder-Next](https://unsloth.ai/docs/models/qwen3-coder-next) | [link](https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF) | — |
18
+ | [**gpt-oss**](https://unsloth.ai/docs/models/gpt-oss-how-to-run-and-fine-tune) | 120B | [link](https://huggingface.co/unsloth/gpt-oss-120b-GGUF) | [link](https://huggingface.co/unsloth/gpt-oss-120b-unsloth-bnb-4bit) |
19
+ | | 20B | [link](https://huggingface.co/unsloth/gpt-oss-20b-GGUF) | [link](https://huggingface.co/unsloth/gpt-oss-20b-unsloth-bnb-4bit) |
20
+ | NVIDIA [Nemotron 3](https://unsloth.ai/docs/models/tutorials/nemotron-3) | 30B | [link](https://huggingface.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF) | — |
21
+ | [**Qwen-Image**](https://unsloth.ai/docs/models/qwen-image-2512) | 2512 | [link](https://huggingface.co/unsloth/Qwen-Image-2512-GGUF) | — |
22
+ | | Edit-2511 | [link](https://huggingface.co/unsloth/Qwen-Image-Edit-2511-GGUF) | — |
23
+ | [**Ministral 3**](https://unsloth.ai/docs/models/tutorials/ministral-3) | 3B | [Instruct](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF) • [Reasoning](https://hface.co/unsloth/Ministral-3-3B-Reasoning-2512-GGUF) | [Instruct](https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-unsloth-bnb-4bit) • [Reasoning](https://huggingface.co/unsloth/Ministral-3-3B-Reasoning-2512-GGUF) |
24
+ | | 8B | [Instruct](https://huggingface.co/unsloth/Ministral-3-8B-Instruct-2512-GGUF) • [Reasoning](https://huggingface.co/unsloth/Ministral-3-8B-Reasoning-2512-GGUF) | [Instruct](https://huggingface.co/unsloth/Ministral-3-8B-Instruct-2512-unsloth-bnb-4bit) • [Reasoning](https://huggingface.co/unsloth/Ministral-3-8B-Reasoning-2512-unsloth-bnb-4bit) |
25
+ | | 14B | [Instruct](https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-GGUF) • [Reasoning](https://ace.co/unsloth/Ministral-3-14B-Reasoning-2512-GGUF) | [Instruct](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-unsloth-bnb-4bit) • [Reasoning](https://huggingface.co/unsloth/Ministral-3-14B-Reasoning-2512-unsloth-bnb-4bit) |
26
+ | [**Devstral 2**](https://unsloth.ai/docs/models/tutorials/devstral-2) | 24B | [link](https://huggingface.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF) | — |
27
+ | | 123B | [link](https://huggingface.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF) | — |
28
+ | **Mistral Large 3** | 675B | [link](https://huggingface.co/unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF) | [link](https://huggingface.co/unsloth/Mistral-Large-3-675B-Instruct-2512-NVFP4) |
29
+ | [**FunctionGemma**](https://unsloth.ai/docs/models/tutorials/functiongemma) | 270M | [link](https://huggingface.co/unsloth/functiongemma-270m-it-GGUF) | — |
30
+ | [**Qwen3-Next**](https://unsloth.ai/docs/models/tutorials/qwen3-next) | 80B-A3B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Instruct-bnb-4bit/) |
31
+ | | 80B-A3B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF) | — |
32
+ | [**Qwen3-VL**](https://unsloth.ai/docs/models/qwen3-vl-how-to-run-and-fine-tune) | 2B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit) |
33
+ | | 2B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit) |
34
+ | | 4B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit) |
35
+ | | 4B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit) |
36
+ | | 8B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit) |
37
+ | | 8B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit) |
38
+ | | 30B-A3B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF) | — |
39
+ | | 30B-A3B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF) | — |
40
+ | | 32B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-32B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-32B-Instruct-unsloth-bnb-4bit) |
41
+ | | 32B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-32B-Thinking-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-32B-Thinking-unsloth-bnb-4bit) |
42
+ | | 235B-A22B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF) | — |
43
+ | | 235B-A22B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF) | — |
44
+ | [**Qwen3-2507**](https://unsloth.ai/docs/models/tutorials/qwen3-next) | 30B-A3B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF) | — |
45
+ | | 30B-A3B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF) | — |
46
+ | | 235B-A22B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF/) | — |
47
+ | | 235B-A22B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF/) | — |
48
+ | [**Qwen3-Coder**](https://unsloth.ai/docs/models/qwen3-coder-how-to-run-locally) | 30B-A3B | [link](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF) | — |
49
+ | | 480B-A35B | [link](https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF) | — |
50
+ | [**GLM**](https://unsloth.ai/docs/models/tutorials/glm-4.6-how-to-run-locally) | 4.7 | [link](https://huggingface.co/unsloth/GLM-4.7-GGUF) | — |
51
+ | | 4.6V-Flash | [link](https://huggingface.co/unsloth/GLM-4.6V-Flash-GGUF) | — |
52
+ | | 4.6 | [link](https://huggingface.co/unsloth/GLM-4.6-GGUF) | — |
53
+ | | 4.5-Air | [link](https://huggingface.co/unsloth/GLM-4.5-Air-GGUF) | — |
54
+ | [**DeepSeek-V3.1**](https://unsloth.ai/docs/models/tutorials/deepseek-v3.1-how-to-run-locally) | Terminus | [link](https://huggingface.co/unsloth/DeepSeek-V3.1-Terminus-GGUF) | — |
55
+ | | V3.1 | [link](https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF) | — |
56
+ | **Granite-4.0** | H-Small | [link](https://huggingface.co/unsloth/granite-4.0-h-small-GGUF) | [link](https://huggingface.co/unsloth/granite-4.0-h-small-unsloth-bnb-4bit) |
57
+ | **Kimi-K2** | Thinking | [link](https://huggingface.co/unsloth/Kimi-K2-Thinking-GGUF) | — |
58
+ | | 0905 | [link](https://huggingface.co/unsloth/Kimi-K2-Instruct-0905-GGUF) | — |
59
+ | **Gemma 3n** | E2B | [link](https://huggingface.co/unsloth/gemma-3n-E2B-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3n-E2B-it-unsloth-bnb-4bit) |
60
+ | | E4B | [link](https://huggingface.co/unsloth/gemma-3n-E4B-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit) |
61
+ | **DeepSeek-R1-0528** | R1-0528-Qwen3-8B | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-unsloth-bnb-4bit) |
62
+ | | R1-0528 | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF) | — |
63
+
64
+ #### DeepSeek models:
65
+
66
+ | Model | Variant | GGUF | Instruct (4-bit) |
67
+ | ----------------- | ---------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
68
+ | **DeepSeek-V3.1** | Terminus | [link](https://huggingface.co/unsloth/DeepSeek-V3.1-Terminus-GGUF) | |
69
+ | | V3.1 | [link](https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF) | |
70
+ | **DeepSeek-V3** | V3-0324 | [link](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF) | — |
71
+ | | V3 | [link](https://huggingface.co/unsloth/DeepSeek-V3-GGUF) | — |
72
+ | **DeepSeek-R1** | R1-0528 | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF) | — |
73
+ | | R1-0528-Qwen3-8B | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-unsloth-bnb-4bit) |
74
+ | | R1 | [link](https://huggingface.co/unsloth/DeepSeek-R1-GGUF) | — |
75
+ | | R1 Zero | [link](https://huggingface.co/unsloth/DeepSeek-R1-Zero-GGUF) | — |
76
+ | | Distill Llama 3 8 B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit) |
77
+ | | Distill Llama 3.3 70 B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B-bnb-4bit) |
78
+ | | Distill Qwen 2.5 1.5 B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit) |
79
+ | | Distill Qwen 2.5 7 B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit) |
80
+ | | Distill Qwen 2.5 14 B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit) |
81
+ | | Distill Qwen 2.5 32 B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF) | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit) |
82
+
83
+ #### Llama models:
84
+
85
+ | Model | Variant | GGUF | Instruct (4-bit) |
86
+ | ------------- | ------------------- | ------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------- |
87
+ | **Llama 4** | Scout 17 B-16 E | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit) |
88
+ | | Maverick 17 B-128 E | [link](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF) | — |
89
+ | **Llama 3.3** | 70 B | [link](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-GGUF) | [link](https:huggingface.co/unsloth/Llama-3.3-70B-Instruct-bnb-4bit) |
90
+ | **Llama 3.2** | 1 B | [link](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-bnb-4bit) |
91
+ | | 3 B | [link](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit) |
92
+ | | 11 B Vision | — | [link](https://huggingface.co/unsloth/Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bit) |
93
+ | | 90 B Vision | — | [link](https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit) |
94
+ | **Llama 3.1** | 8 B | [link](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-GGUF | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit) |
95
+ | | 70 B | — | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit) |
96
+ | | 405 B | — | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit) |
97
+ | **Llama 3** | 8 B | — | [link](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) |
98
+ | | 70 B | — | [link](https://huggingface.co/unsloth/llama-3-70b-bnb-4bit) |
99
+ | **Llama 2** | 7 B | — | [link](https://huggingface.co/unsloth/llama-2-7b-chat-bnb-4bit) |
100
+ | | 13 B | — | [link](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit) |
101
+ | **CodeLlama** | 7 B | — | [link](https://huggingface.co/unsloth/codellama-7b-bnb-4bit) |
102
+ | | 13 B | — | [link](https://huggingface.co/unsloth/codellama-13b-bnb-4bit) |
103
+ | | 34 B | — | [link](https://huggingface.co/unsloth/codellama-34b-bnb-4bit) |
104
+
105
+ #### Gemma models:
106
+
107
+ | Model | V | GGUF | Instruct (4-bit) |
108
+ | ----------------- | ------------- | ----------------------------------------------------------------- | ---------------------------------------------------------------------------- |
109
+ | **FunctionGemma** | 270M | [link](https://huggingface.co/unsloth/functiongemma-270m-it-GGUF) | — |
110
+ | **Gemma 3n** | E2B | ​[link](https://huggingface.co/unsloth/gemma-3n-E2B-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3n-E2B-it-unsloth-bnb-4bit) |
111
+ | | E4B | [link](https://huggingface.co/unsloth/gemma-3n-E4B-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit) |
112
+ | **Gemma 3** | 270M | [link](https://huggingface.co/unsloth/gemma-3-270m-it-GGUF) | [link](https://hugface.co/unsloth/gemma-3-270m-it) |
113
+ | | 1 B | [link](https://huggingface.co/unsloth/gemma-3-1b-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3-1b-it-unsloth-bnb-4bit) |
114
+ | | 4 B | [link](https://huggingface.co/unsloth/gemma-3-4b-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3-4b-it-unsloth-bnb-4bit) |
115
+ | | 12 B | [link](https://huggingface.co/unsloth/gemma-3-12b-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3-12b-it-unsloth-bnb-4bit) |
116
+ | | 27 B | [link](https://huggingface.co/unsloth/gemma-3-27b-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-3-27b-it-unsloth-bnb-4bit) |
117
+ | **MedGemma** | 4 B (vision) | [link](https://huggingface.co/unsloth/medgemma-4b-it-GGUF) | [link](https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit) |
118
+ | | 27 B (vision) | [link](https://huggingface.co/unsloth/medgemma-27b-it-GGUF) | [link](https://huggingface.co/unsloth/medgemma-27b-text-it-unsloth-bnb-4bit) |
119
+ | **Gemma 2** | 2 B | [link](https://huggingface.co/unsloth/gemma-2-it-GGUF) | [link](https://huggingface.co/unsloth/gemma-2-2b-it-bnb-4bit) |
120
+ | | 9 B | — | [link](https://huggingface.co/unsloth/gemma-2-9b-it-bnb-4bit) |
121
+ | | 27 B | — | [link](https://huggingface.co/unsloth/gemma-2-27b-it-bnb-4bit) |
122
+
123
+ #### Qwen models:
124
+
125
+ | Model | Variant | GGUF | Instruct (4-bit) |
126
+ | ---------------------------------------------------------------------------- | ------------------ | ---------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
127
+ | [**Qwen3-VL**](https://unsloth.ai/docs/models/qwen3-vl-how-to-run-and-fine-tune) | 2B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit) |
128
+ | | 2B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit) |
129
+ | | 4B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit) |
130
+ | | 4B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit) |
131
+ | | 8B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit) |
132
+ | | 8B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit) |
133
+ | **Qwen3-Coder** | 30B-A3B | [link](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF) | — |
134
+ | | 480B-A35B | [link](https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF) | — |
135
+ | [**Qwen3-2507**](https://unsloth.ai/docs/models/tutorials/qwen3-next) | 30B-A3B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF) | — |
136
+ | | 30B-A3B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF) | — |
137
+ | | 235B-A22B-Thinking | [link](https://huggingface.co/unsloth/Qwen3-235B-A22king-2507-GGUF/) | — |
138
+ | | 235B-A22B-Instruct | [link](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF/) | — |
139
+ | **Qwen 3** | 0.6 B | [link](https://huggingface.co/unsloth/Qwen3-0.6B-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-0.6B-unsloth-bnb-4bit) |
140
+ | | 1.7 B | [link](https://huggingface.co/unsloth/Qwen3-1.7B-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-1.7B-unsloth-bnb-4bit) |
141
+ | | 4 B | [link](h://huggingface.co/unsloth/Qwen3-4B-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-4B-unsloth-bnb-4bit) |
142
+ | | 8 B | [link](https://huggingface.co/unsloth/Qwen3-8B-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-8B-unsloth-bnb-4bit) |
143
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen3-14B-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-14B-unsloth-bnb-4bit) |
144
+ | | 30 B-A3B | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-bnb-4bit) |
145
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen3-32B-GGUF) | [link](https://huggingface.co/unsloth/Qwen3-32B-unsloth-bnb-4bit) |
146
+ | | 235 B-A22B | [link](https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF) | — |
147
+ | **Qwen 2.5 Omni** | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-Omni-3B-GGUF) | — |
148
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-Omni-7B-GGUF) | — |
149
+ | **Qwen 2.5 VL** | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct-unsloth-bnb-4bit) |
150
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit) |
151
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit) |
152
+ | | 72 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct-unsloth-bnb-4bit) |
153
+ | **Qwen 2.5** | 0.5 B | — | [link](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit) |
154
+ | | 1.5 B | — | [link](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit) |
155
+ | | 3 B | — | [link](https://huggingface.co/unsloth/Qwen2.5-3B-Instruct-bnb-4bit) |
156
+ | | 7 B | — | [link](huggingface.co/unsloth/Qwen2.5-7B-Instruct-bnb-4bit) |
157
+ | | 14 B | — | [link](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct-bnb-4bit) |
158
+ | | 32 B | — | [link](https://huggingface.co/unsloth/Qwen2.5-32B-Instruct-bnb-4bit) |
159
+ | | 72 B | — | [link](https://huggingface.co/unsloth/Qwen2.5-72B-Instruct-bnb-4bit) |
160
+ | **Qwen 2.5 Coder (128 K)** | 0.5 B | [link](https://huggingface.co/unsloth/Qwen2er-0.5B-Instruct-128K-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-bnb-4bit) |
161
+ | | 1.5 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-128K-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit) |
162
+ | | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-128K-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit) |
163
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit) |
164
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-128K-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit) |
165
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-128K-GGUF) | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit) |
166
+ | **QwQ** | 32 B | [link](https://huggingface.co/unsloth/QwQ-32B-GGUF) | [link](https://huggingface.co/unsloth/QwQ-32B-unsloth-bnb-4bit) |
167
+ | **QVQ (preview)** | 72 B | — | [link](https://huggingface.co/unsloth/QVQ-72B-Preview-bnb-4bit) |
168
+ | **Qwen 2 (chat)** | 1.5 B | — | [link](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct-bnb-4bit) |
169
+ | | 7 B | — | [link](https://huggingface.co/unsloth/Qwen2-7B-Instruct-bnb-4bit) |
170
+ | | 72 B | — | [link](https://huggingface.co/unsloth/Qwen2-72B-Instruct-bnb-4bit) |
171
+ | **Qwen 2 VL** | 2 B | — | [link](https://huggingface.co/unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit) |
172
+ | | 7 B | — | [link](https://huggingface.co/unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit) |
173
+ | | 72 B | — | [link](https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct-bnb-4bit) |
174
+
175
+ #### Mistral models:
176
+
177
+ | Model | Variant | GGUF | Instruct (4-bit) |
178
+ | ----------------- | ----------------- | ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- |
179
+ | **Magistral** | Small (2506) | k](https://huggingface.co/unsloth/Magistral-Small-2506-GGUF) | [link](https://huggingface.co/unsloth/Magistral-Small-2506-unsloth-bnb-4bit) |
180
+ | | Small (2509) | [link](https://huggingface.co/unsloth/Magistral-Small-2509-GGUF) | [link](https://huggingface.co/unsloth/Magistral-Small-2509-unsloth-bnb-4bit) |
181
+ | | Small (2507) | [link](https://huggingface.co/unsloth/Magistral-Small-2507-GGUF) | [link](https://huggingface.co/unsloth/Magistral-Small-2507-unsloth-bnb-4bit) |
182
+ | **Mistral Small** | 3.2-24 B (2506) | [link](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF) | [link](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit) |
183
+ | | 3.1-24 B (2503) | [link](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF) | [link](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-unsloth-bnb-4bit) |
184
+ | | 3-24 B (2501) | [link](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501-GGUF) | [link](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit) |
185
+ | | 2409-22 B | — | [link](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409-bnb-4bit) |
186
+ | **Devstral** | Small-24 B (2507) | [link](https://huggingface.co/unsloth/Devstral-Small-2507-GGUF) | [link](https://huggingface.co/unsloth/Devstral-Small-2507-unsloth-bnb-4bit) |
187
+ | | Small-24 B (2505) | [link](https://huggingface.co/unsloth/Devstral-Small-2505-GGUF) | [link](https://huggingface.co/unsloth/Devstral-Small-2505-unsloth-bnb-4bit) |
188
+ | **Pixtral** | 12 B (2409) | — | k](https://huggingface.co/unsloth/Pixtral-12B-2409-bnb-4bit) |
189
+ | **Mistral NeMo** | 12 B (2407) | [link](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407-GGUF) | [link](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit) |
190
+ | **Mistral Large** | 2407 | — | [link](https://huggingface.co/unsloth/Mistral-Large-Instruct-2407-bnb-4bit) |
191
+ | **Mistral 7 B** | v0.3 | — | [link](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit) |
192
+ | | v0.2 | — | [link](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) |
193
+ | **Mixtral** | 8 × 7 B | — | [link](https://huggingface.co/unsloth/Mixtral-8x7B-Instruct-v0.1-unsloth-bnb-4bit) |
194
+
195
+ #### Phi models:
196
+
197
+ | Model | Variant | GGUF | Instruct (4-bit) |
198
+ | ----------- | ---------------- | ---------------------------------------------------------------- | ---------------------------------------------------------------------------- |
199
+ | **Phi-4** | Reasoning-plus | [link](https://huggingface.co/unsloth/Phi-4-reasoning-plus-GGUF) | [link](https://huggingface.co/unsloth/Phi-4-reasoning-plus-unsloth-bnb-4bit) |
200
+ | | Reasoning | [link](https://huggingface.co/unsloth/Phi-4-reasoning-GGUF) | [link](https://huggingface.co/unsloth/phi-4-reasoning-unsloth-bnb-4bit) |
201
+ | | Mini-Reasoning | [link](https://huggingface.co/unsloth/Phi-4-mini-reasoning-GGUF) | [link](https://huggingface.co/unsloth/Phi-4-mini-reasoning-unsloth-bnb-4bit) |
202
+ | | Phi-4 (instruct) | [link](https://huggingface.co/unsloth/phi-4-GGUF) | [link](https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit) |
203
+ | | mini (instruct) | [link](https://huggingface.co/unsloth/Phi-4-mini-instruct-GGUF) | [link](https://huggingface.co/unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit) |
204
+ | **Phi-3.5** | mini | — | [link](https://huggingface.co/unsloth/Phi-3.5-mini-instruct-bnb-4bit) |
205
+ | **Phi-3** | mini | — | [link](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct-bnb-4bit) |
206
+ | | medium | — | [link](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct-bnb-4bit) |
207
+
208
+ #### Other (GLM, Orpheus, Smol, Llava etc.) modelsodel | Variant | GGUF | Instruct (4-bit) |
209
+ | --------------- | -------------------- | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------- |
210
+ | GLM | 4.5-Air | [link](https://huggingface.co/unsloth/GLM-4.5-Air-GGUF) | — |
211
+ | | 4.5 | [4.5](https://huggingface.co/unsloth/GLM-4.5-GGUF) | — |
212
+ | | 4-32B-0414 | [4-32B-0414](https://huggingface.co/unsloth/GLM-4-32B-0414-GGUF) | — |
213
+ | **Grok 2** | | [link](https://huggingface.co/unsloth/grok-2-GGUF) | — |
214
+ | **Baidu-ERNIE** | 4.5-21B-A3B-Thinking | [link](https://huggingface.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF) | — |
215
+ | Hunyuan | A13B | [link](https://huggingface.co/unsloth/Hunyuan-A13B-Instruct-GGUF) | — |
216
+ | Orpheus | 0.1-ft (3B) | [link](https://app.gitbook.com/o/HpyELzcNe0topgVLGCZY/s/xhOjnexMCB3dmuQFQ2Zq/) | [link](https://huggingface.co/unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit) |
217
+ | **LLava** | 1.5 (7 B) | — | [link](https://huggingface.co/unsloth/llava-1.5-7b-hf-bnb-4bit) |
218
+ | | 1.6 Mistral (7 B) | [link](https://huggingface.co/unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit) |
219
+ | **TinyLlama** | Chat | — | [link](https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit) |
220
+ | **SmolLM 2** | 135 M | [link](https://huggingface.co/unsloth/SmolLM2-135M-Instruct-GGUF) | [link](https://huggingface.co/unsloth/SmolLM2-135M-Instruct-bnb-4bit) |
221
+ | | 360 M | [link](https://huggingface.co/unsloth/SmolLM2-360M-Instruct-GGUF) | [link](https://huggingface.co/unsloth/SmolLM2-360M-Instruct-bnb-4bit) |
222
+ | | 1.7 B | [link](https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-GGUF) | [link](https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-bnb-4bit) |
223
+ | **Zephyr-SFT** | 7 B | — | [link](https://huggingface.co/unsloth/zephyr-sft-bnb-4bit) |
224
+ | **Yi** | 6 B (v1.5) | — | [link](https://huggingface.co/unsloth/Yi-1.5-6B-bnb-4bit) |
225
+ | | 6 B (v1.0) | — | [link](https://huggingface.co/unsloth/yi-6b-bnb-4bit) |
226
+ | | 34 B (chat) | — | [link](https://huggingface.co/unsloth/yi-34b-chat-bnb-4bit) |
227
+ | | 34 B (base) | — | [link](https://huggingface.co/unsloth/yi-34b-bnb-4bit) |
228
+ | {% endtab %} | | | |
229
+
230
+ {% tab title="• Instruct 16-bit" %}
231
+ 16-bit and 8-bit Instruct models are used for inference or fine-tuning:
232
+
233
+ #### New models:
234
+
235
+ | Model | Variant | Instruct (16-bit) |
236
+ | -------------------- | ---------------------- | -------------------------------------------------------------------------- |
237
+ | **gpt-oss** (new) | 20b | [link](https://huggingface.co/unsloth/gpt-oss-20b) |
238
+ | | 120b | [link](https://huggingface.co/unsloth/gpt-oss-120b) |
239
+ | **Gemma 3n** | E2B | [link](https://huggingface.co/unsloth/gemma-3n-E4B-it) |
240
+ | | E4B | [link](https://huggingface.co/unsloth/gemma-3n-E2B-it) |
241
+ | **DeepSeek-R1-0528*| R1-0528-Qwen3-8B | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B) |
242
+ | | R1-0528 | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528) |
243
+ | **Mistral** | Small 3.2 24B (2506) | [link](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506) |
244
+ | | Small 3.1 24B (2503) | [link](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503) |
245
+ | | Small 3.0 24B (2501) | [link](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501) |
246
+ | | Magistral Small (2506) | [link](https://huggingface.co/unsloth/Magistral-Small-2506) |
247
+ | **Qwen 3** | 0.6 B | [link](https://huggingface.co/unsloth/Qwen3-0.6B) |
248
+ | | 1.7 B | [link](https://huggingface.co/unsloth/Qwen3-1.7B) |
249
+ | | 4 B | [link](https://huggingface.co/unsloth/Qwen3-4B) |
250
+ | | 8 B | [link](https://huggingface.co/unsloth/Qwen3-8B) |
251
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen3-14B) |
252
+ | | 30B-A3B | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B) |
253
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen3-32B) |
254
+ | | 235B-A22B | [link](https://huggingface.co/unsloth/Qwen3-235B-A22B) |
255
+ | **Llama 4** | Scout 17B-16E | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct) |
256
+ | | Maverick 17B-128E | [link](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct) |
257
+ | **Qwen 2.5 Omni** | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-Omni-3B) |
258
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-Omni-7B) |
259
+ | **Phi-4** | Reasoning-plus | [link](https://huggingface.co/unsloth/Phi-4-reasoning-plus) |
260
+ | | Reasoning | [link](https://huggingface.co/unsloth/Phi-4-reasoning) |
261
+
262
+ #### DeepSeek models
263
+
264
+ | Model | Variant | Instruct (16-bit) |
265
+ | --------------- | --------------------- | -------------------------------------------------------------------- |
266
+ | **DeepSeek-V3** | V3-0324 | [link](https://huggingface.co/unsloth/DeepSeek-V3-0324) |
267
+ | | V3 | [link](https://huggingface.co/unsloth/DeepSeek-V3) |
268
+ | **DeepSeek-R1** | R1-0528 | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528) |
269
+ | | R1-0528-Qwen3-8B | [link](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B) |
270
+ | | R1 | [link](https://huggingface.co/unsloth/DeepSeek-R1) |
271
+ | | R1 Zero | [link](https://huggingface.co/unsloth/DeepSeek-R1-Zero) |
272
+ | | Distill Llama 3 8B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B) |
273
+ | | Distill Llama 3.3 70B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B) |
274
+ | | Distill Qwen 2.5 1.5B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B) |
275
+ | | Distill Qwen 2.5 7B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B) |
276
+ | | Distill Qwen 2.5 14B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B) |
277
+ | | Distill Qwen 2.5 32B | [link](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B) |
278
+
279
+ #### Llama models
280
+
281
+ | Family | Variant | Instruct (16-bit) |
282
+ | ------------- | ----------------- | ------------------------------------------------------------------------- |
283
+ | **Llama 4** | Scout 17B-16E | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct) |
284
+ | | Maverick 17B-128E | [link](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct) |
285
+ | **Llama 3.3** | 70 B | [link](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct) |
286
+ | **Llama 3.2** | 1 B | [link](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct) |
287
+ | | 3 B | [link](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct) |
288
+ | | 11 B Vision | [link](https://huggingface.co/unsloth/Llama-3.2-11B-Vision-Instruct) |
289
+ | | 90 B Vision | [link](https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct) |
290
+ | **Llama 3.1** | 8 B | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) |
291
+ | | 70 B | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-70B-Instruct) |
292
+ | | 405 B | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-405B-Instruct) |
293
+ | **Llama 3** | 8 B | [link](https://huggingface.co/unsloth/llama-3-8b-Instruct) |
294
+ | | 70 B | [link](https://huggingface.co/unsloth/llama-3-70b-Instruct) |
295
+ | **Llama 2** | 7 B | [link](https://huggingface.co/unsloth/llama-2-7b-chat) |
296
+
297
+ #### Gemma models:
298
+
299
+ | Model | Variant | Instruct (16-bit) |
300
+ | ------------ | ------- | ------------------------------------------------------ |
301
+ | **Gemma 3n** | E2B | [link](https://huggingface.co/unsloth/gemma-3n-E4B-it) |
302
+ | | E4B | [link](https://huggingface.co/unsloth/gemma-3n-E2B-it) |
303
+ | **Gemma 3** | 1 B | [link](https://huggingface.co/unsloth/gemma-3-1b-it) |
304
+ | | 4 B | [link](https://huggingface.co/unsloth/gemma-3-4b-it) |
305
+ | | 12 B | [link](https://huggingface.co/unsloth/gemma-3-12b-it) |
306
+ | | 27 B | [link](https://huggingface.co/unsloth/gemma-3-27b-it) |
307
+ | **Gemma 2** | 2 B | [link](https://huggingface.co/unsloth/gemma-2b-it) |
308
+ | | 9 B | [link](https://huggingface.co/unsloth/gemma-9b-it) |
309
+ | | 27 B | [link](https://huggingface.co/unsloth/gemma-27b-it) |
310
+
311
+ #### Qwen models:
312
+
313
+ | Family | Variant | Instruct (16-bit) |
314
+ | ------------------------ | --------- | ----------------------------------------------------------------------- |
315
+ | **Qwen 3** | 0.6 B | [link](https://huggingface.co/unsloth/Qwen3-0.6B) |
316
+ | | 1.7 B | [link](https://huggingface.co/unsloth/Qwen3-1.7B) |
317
+ | | 4 B | [link](https://huggingface.co/unsloth/Qwen3-4B) |
318
+ | | 8 B | [link](https://huggingface.co/unsloth/Qwen3-8B) |
319
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen3-14B) |
320
+ | | 30B-A3B | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B) |
321
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen3-32B) |
322
+ | | 235B-A22B | [link](https://huggingface.co/unsloth/Qwen3-235B-A22B) |
323
+ | **Qwen 2.5 Omni** | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-Omni-3B) |
324
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-Omni-7B) |
325
+ | **Qwen 2.5 VL** | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct) |
326
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct) |
327
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct) |
328
+ | | 72 B | [link](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct) |
329
+ | **Qwen 2.5** | 0.5 B | [link](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct) |
330
+ | | 1.5 B | [link](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct) |
331
+ | | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-3B-Instruct) |
332
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct) |
333
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct) |
334
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen2.5-32B-Instruct) |
335
+ | | 72 B | [link](https://huggingface.co/unsloth/Qwen2.5-72B-Instruct) |
336
+ | **Qwen 2.5 Coder 128 K** | 0.5 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-128K) |
337
+ | | 1.5 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-128K) |
338
+ | | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-128K) |
339
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K) |
340
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-128K) |
341
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-128K) |
342
+ | **QwQ** | 32 B | [link](https://huggingface.co/unsloth/QwQ-32B) |
343
+ | **QVQ (preview)** | 72 B | — |
344
+ | **Qwen 2 (Chat)** | 1.5 B | [link](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct) |
345
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2-7B-Instruct) |
346
+ | | 72 B | [link](https://huggingface.co/unsloth/Qwen2-72B-Instruct) |
347
+ | **Qwen 2 VL** | 2 B | [link](https://huggingface.co/unsloth/Qwen2-VL-2B-Instruct) |
348
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2-VL-7B-Instruct) |
349
+ | | 72 B | [link](https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct) |
350
+
351
+ #### Mistral models:
352
+
353
+ | Model | Variant | Instruct (16-bit) |
354
+ | -------------- | -------------- | ------------------------------------------------------------------ |
355
+ | **Mistral** | Small 2409-22B | [link](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) |
356
+ | **Mistral** | Large 2407 | [link](https://huggingface.co/unsloth/Mistral-Large-Instruct-2407) |
357
+ | **Mistral** | 7B v0.3 | [link](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3) |
358
+ | **Mistral** | 7B v0.2 | [link](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2) |
359
+ | **Pixtral** | 12B 2409 | [link](https://huggingface.co/unsloth/Pixtral-12B-2409) |
360
+ | **Mixtral** | 8×7B | [link](https://huggingface.co/unsloth/Mixtral-8x7B-Instruct-v0.1) |
361
+ | **Mistral NeMo** | 12B 2407 | [link](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407) |
362
+ | **Devstral** | Small 2505 | [link](https://huggingface.co/unsloth/Devstral-Small-2505) |
363
+
364
+ #### Phi models:
365
+
366
+ | Model | Variant | Instruct (16-bit) |
367
+ | ----------- | -------------- | --------------------------------------------------------------- |
368
+ | **Phi-4** | Reasoning-plus | [link](https://huggingface.co/unsloth/Phi-4-reasoning-plus) |
369
+ | | Reasoning | [link](https://huggingface.co/unsloth/Phi-4-reasoning) |
370
+ | | Phi-4 (core) | [link](https://huggingface.co/unsloth/Phi-4) |
371
+ | | Mini-Reasoning | [link](https://huggingface.co/unsloth/Phi-4-mini-reasoning) |
372
+ | | Mini | [link](https://huggingface.co/unsloth/Phi-4-mini) |
373
+ | **Phi-3.5** | Mini | [link](https://huggingface.co/unsloth/Phi-3.5-mini-instruct) |
374
+ | **Phi-3** | Mini | [link](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct) |
375
+ | | Medium | [link](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct) |
376
+
377
+ #### Text-to-Speech (TTS) models:
378
+
379
+ | Model | Instruct (16-bit) |
380
+ | ---------------------- | ---------------------------------------------------------------- |
381
+ | Orpheus-3B (v0.1 ft) | [link](https://huggingface.co/unsloth/orpheus-3b-0.1-ft) |
382
+ | Orpheus-3B (v0.1 pt) | [link](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained) |
383
+ | Sesame-CSM 1B | [link](https://huggingface.co/unsloth/csm-1b) |
384
+ | Whisper Large V3 (STT) | [link](https://huggingface.co/unsloth/whisper-large-v3) |
385
+ | Llasa-TTS 1B | [link](https://huggingface.co/unsloth/Llasa-1B) |
386
+ | Spark-TTS 0.5B | [link](https://huggingface.co/unsloth/Spark-TTS-0.5B) |
387
+ | Oute-TTS 1B | [link](https://huggingface.co/unsloth/Llama-OuteTTS-1.0-1B) |
388
+ | {% endtab %} | |
389
+
390
+ {% tab title="• Base 4 & 16-bit" %}
391
+ Base models are usually used for fine-tuning purposes:
392
+
393
+ #### New models:
394
+
395
+ | Model | riant | Base (16-bit) | Base (4-bit) |
396
+ | ------------ | ----------------- | ---------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
397
+ | **Gemma 3n** | E2B | [link](https://huggingface.co/unsloth/gemma-3n-E2B) | [link](https://huggingface.co/unsloth/gemma-3n-E2B-unsloth-bnb-4bit) |
398
+ | | E4B | [link](https://huggingface.co/unsloth/gemma-3n-E4B) | [link](https://huggingface.co/unsloth/gemma-3n-E4B-unsloth-bnb-4bit) |
399
+ | **Qwen 3** | 0.6 B | [link](https://huggingface.co/unsloth/Qwen3-0.6B-Base) | [link](https://huggingface.co/unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit) |
400
+ | | 1.7 B | [link](https://huggingface.co/unsloth/Qwen3-1.7B-Base) | [link](https://huggingface.co/unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit) |
401
+ | | 4 B | [link](https://huggingface.co/unsloth/Qwen3-4B-Base) | [link](https://huggingface.co/unsloth/Qwen3-4B-Base-unsloth-bnb-4bit) |
402
+ | | 8 B | [link](https://huggingface.co/unsloth/Qwen3-8B-Base) | [link](https://huggingface.co/unsloth/Qwen3-8B-Base-unsloth-bnb-4bit) |
403
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen3-14B-Base) | [link](https://huggingface.co/unsloth/Qwen3-14B-Base-unsloth-bnb-4bit) |
404
+ | | 30B-A3B | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base) | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base-bnb-4bit) |
405
+ | **Llama 4** | Scout 17B 16E | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E) | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit) |
406
+ | | Maverick 17B 128E | [link](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E) | — |
407
+
408
+ #### **Llama models:**
409
+
410
+ | Model | Variant | Base (16-bit) | Base (4-bit) |
411
+ | ------------- | ----------------- | ---------------------------------------------------------------- | ----------------------------------------------------------- |
412
+ | **Llama 4** | Scout 17B 16E | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E) | — |
413
+ | | Maverick 17B 128E | [link](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E) | — |
414
+ | **Llama 3.3** | 70 B | [link](https://huggingface.co/Llama-3.3-70B) | — |
415
+ | **Llama 3.2** | 1 B | [link](https://huggingface.co/unsloth/Llama-3.2-1B) | — |
416
+ | | 3 B | [link](https://huggingface.co/unsloth/Llama-3.2-3B) | — |
417
+ | | 11 B Vision | [link](https://huggingface.co/unsloth/Llama-3.2-11B-Vision) | — |
418
+ | | 90 B Vision | [link](https://huggingface.co/unsloth/Llama-3.2-90B-Vision) | — |
419
+ | **Llama 3.1** | 8 B | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) | — |
420
+ | | 70 B | [link](https://huggingface.co/unsloth/Meta-Lla | — |
421
+ | **Llama 3** | 8 B | [link](https://huggingface.co/unsloth/llama-3-8b) | [link](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) |
422
+ | **Llama 2** | 7 B | [link](https://huggingface.co/unsloth/llama-2-7b) | [link](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) |
423
+ | | 13 B | [link](https://huggingface.co/unsloth/llama-2-13b) | [link](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit) |
424
+
425
+ #### **Qwen models:**
426
+
427
+ | Model | Variant | Base (16-bit) | Base (4-bit) |
428
+ | ------------ | ------- | --------------------------------------------------------- | -------------------------------------------------------------------------- |
429
+ | **Qwen 3** | 0.6 B | [link](https://huggingface.co/unsloth/Qwen3-0.6B-Base) | [link](s://huggingface.co/unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit) |
430
+ | | 1.7 B | [link](https://huggingface.co/unsloth/Qwen3-1.7B-Base) | [link](https://huggingface.co/unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit) |
431
+ | | 4 B | [link](https://huggingface.co/unsloth/Qwen3-4B-Base) | [link](https://huggingface.co/unsloth/Qwen3-4B-Base-unsloth-bnb-4bit) |
432
+ | | 8 B | [link](https://huggingface.co/unsloth/Qwen3-8B-Base) | [link](https://huggingface.co/unsloth/Qwen3-8B-Base-unsloth-bnb-4bit) |
433
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen3-14B-Base) | [link](https://huggingface.co/unsloth/Qwen3-14B-Base-unsloth-bnb-4bit) |
434
+ | | 30B-A3B | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base) | [link](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base-unsloth-bnb-4bit) |
435
+ | **Qwen 2.5** | 0.5 B | [link](https://huggingface.co/unsloth/Qwen2.5-0.5B) | [link](https://huggingface.co/unsloth/Qwen2.5-0.5B-bnb-4bit) |
436
+ | | 1.5 B | [link](https://huggingface.co/unsloth/Qwen2.5-1.5B) | [link](https://huggingface.co/unsloth/Qwen2.5-1.5B-bnb-4bit) |
437
+ | | 3 B | [link](https://huggingface.co/unsloth/Qwen2.5-3B) | [link](https://huggingface.co/unsloth/Qwen2.5-3B-bnb-4bit) |
438
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2.5-7B) | [link](https://huggingface.co/unsloth/Qwen2.5-7B-bnb-4bit) |
439
+ | | 14 B | [link](https://huggingface.co/unsloth/Qwen2.5-14B) | [link](https://huggingface.co/unsloth/Qwen2.5-14B-bnb-4bit) |
440
+ | | 32 B | [link](https://huggingface.co/unsloth/Qwen2.5-32B) | [link](https://huggingface.co/unsloth/Qwen2.5-32B-bnb-4bit) |
441
+ | | 72 B | [link](https://huggingface.co/unsloth/Qwen2.5-72B) | [link](https://huggingface.co/unsloth/Qwen2.5-72B-bnb-4bit) |
442
+ | **Qwen 2** | 1.5 B | [link](https://huggingface.co/unsloth/Qwen2-1.5B) | [link](https://huggingface.co/unsloth/Qwen2-1.5B-bnb-4bit) |
443
+ | | 7 B | [link](https://huggingface.co/unsloth/Qwen2-7B) | [link](https://huggingface.co/unsloth/Qwen2-7B-bnb-4bit) |
444
+
445
+ #### **Llama models:**
446
+
447
+ | Model | Variant | Base (16-bit) | Base (4-bit) |
448
+ | ------------- | ----------------- | ---------------------------------------------------------------- | ----------------------------------------------------------- |
449
+ | **Llama 4** | Scout 17B 16E | [link](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E) | — |
450
+ | | Maverick 17B 128E | [link](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E) | — |
451
+ | **L.3** | 70 B | [link](https://huggingface.co/unsloth/Llama-3.3-70B) | — |
452
+ | **Llama 3.2** | 1 B | [link](https://huggingface.co/unsloth/Llama-3.2-1B) | — |
453
+ | | 3 B | [link](https://huggingface.co/unsloth/Llama-3.2-3B) | — |
454
+ | | 11 B Vision | [link](https://huggingface.co/unsloth/Llama-3.2-11B-Vision) | — |
455
+ | | 90 B Vision | [link](https://huggingface.co/unsloth/Llama-3.2-90B-Vision) | — |
456
+ | **Llama 3.1** | 8 B | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) | — |
457
+ | | 7 | [link](https://huggingface.co/unsloth/Meta-Llama-3.1-70B) | — |
458
+ | **Llama 3** | 8 B | [link](https://huggingface.co/unsloth/llama-3-8b) | [link](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) |
459
+ | **Llama 2** | 7 B | [link](https://huggingface.co/unsloth/llama-2-7b) | [link](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) |
460
+ | | 13 B | [link](https://huggingface.co/unsloth/llama-2-13b) | [link](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit) |
461
+
462
+ #### **Gemma models**
463
+
464
+ | Model | Variant | Base (16-bit) | Base (4-bit) |
465
+ | ----------- | ------- | ----------------------------------------------------- | ---------------------------------------------------------------------- |
466
+ | **Gemma 3** | 1 B | [link](https://huggine.co/unsloth/gemma-3-1b-pt) | [link](https://huggingface.co/unsloth/gemma-3-1b-pt-unsloth-bnb-4bit) |
467
+ | | 4 B | [link](https://huggingface.co/unsloth/gemma-3-4b-pt) | [link](https://huggingface.co/unsloth/gemma-3-4b-pt-unsloth-bnb-4bit) |
468
+ | | 12 B | [link](https://huggingface.co/unsloth/gemma-3-12b-pt) | [link](https://huggingface.co/unsloth/gemma-3-12b-pt-unsloth-bnb-4bit) |
469
+ | | 27 B | [link](https://huggingface.co/unsloth/gemma-3-27b-pt) | [link](https://huggingface.co/unsloth/gemma-3-27b-pt-unsloth-bnb-4bit) |
470
+ | **Gemma 2** | 2 B | [link](https://huggingface.co/unsloth/gemma-2-2b) | — |
471
+ | | 9 B | [link](https://huggingface.co/unsloth/gemma-2-9b) | — |
472
+ | | 27 B | [link](https://huggingface.co/unsloth/gemma-2-27b) | — |
473
+
474
+ #### **Mistral models:**
475
+
476
+ | Model | Variant | Base (16-bit) | Base (4-bit) |
477
+ | ----------- | ---------------- | ------------------------------------------------------------------ | --------------------------------------------------------------- |
478
+ | **Mistral** | Small 24B 2501 | [link](https://huggingface.co/unsloth/Mistral-Small-24B-Base-2501) | — |
479
+ | | NeMo 12B 2407 | [link](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407) | — |
480
+ | | 7B v0.3 | [link](https://huggingface.co/unsloth/mistral-7b-v0.3) | [link](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) |
481
+ | | 7B v0.2 | [link](https://huggingface.co/unsloth/mistral-7b-v0.2) | [link](https://huggingf/unsloth/mistral-7b-v0.2-bnb-4bit) |
482
+ | | Pixtral 12B 2409 | [link](https://huggingface.co/unsloth/Pixtral-12B-Base-2409) | — |
483
+
484
+ #### **Other (TTS, TinyLlama) models:**
485
+
486
+ | Model | Variant | Base (16-bit) | Base (4-bit) |
487
+ | -------------- | -------------- | ---------------------------------------------------------------- | --------------------------------------------------------------------------------- |
488
+ | **TinyLlama** | 1.1 B (Base) | [link](https://huggingface.co/unsloth/tinyllama) | [link](https://huggingface.co/unsloth/tinyllama-bnb-4bit) |
489
+ | **Orpheus-3b** | 0.1-pretrained | [link](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained) | [link](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained-unsloth-bnb-4bit) |
490
+ | {% endtab %} | | | |
491
+
492
+ {% tab title="• FP8" %}
493
+ You can use our FP8 uploads for training or serving/deployment.
494
+
495
+ FP8 Dynamic offers slightly faster training and lower VRAM usage than FP8 Block, but with a small trade-off in accuracy.
496
+
497
+ | Model | Variant | FP8 (Dynamic / Block) |
498
+ | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |
499
+ | Qwen3 | Coder-Next | [Dynamic](https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8) |
500
+ | GLM | 4.7-Flash | [Dynamic](https://huggingface.co/unsloth/GLM-4.7-Flash-FP8-Dynamic) |
501
+ | **Llama 3.3** | 70B Instruct | [Dynamic](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-FP8-Block) |
502
+ | **Llama 3.2** | 1B Base | [Dynamic](https://huggingface.co/unsloth/Llama-3.2-1B-FP8-Dnamic) · [Block](https://huggingface.co/unsloth/Llama-3.2-1B-FP8-Block) |
503
+ | | 1B Instruct | [Dynamic](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-FP8-Block) |
504
+ | | 3B Base | [Dynamic](https://huggingface.co/unsloth/Llama-3.2-3B-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Llama-3.2-3B-FP8-Block) |
505
+ | | 3B Instruct | [Dynamic](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-FP8-Block) |
506
+ | **Llama 3.1** | 8B Bas | [Dynamic](https://huggingface.co/unsloth/Llama-3.1-8B-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Llama-3.1-8B-FP8-Block) |
507
+ | | 8B Instruct | [Dynamic](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-FP8-Block) |
508
+ | | 70B Base | [Dynamic](https://huggingface.co/unsloth/Llama-3.1-70B-FP8-Dynamic) · [Block](https://huggingface.co/unsloth/Llama-3.1-70B-FP8-Block) |
509
+ | **Qwen3** | 0.6B | [FP8](https://huggingface.co/unsloth/Qwen3-0.6B-FP8) |
510
+ | | 1.7B | [FP8](https://huggingface.co/unsloth/Qwen3-1.7B-FP8) |
511
+ | | 4B | [FP8](https://huggingface.co/unsloth/Qwen3-4B-FP8) |
512
+ | | 8B | [FP8](https://huggingface.co/unsloth/Qwen3-8B-FP8) |
513
+ | | 14B | [FP8](https://huggingface.co/unsloth/Qwen3-14B-FP8) |
514
+ | | 32B | [FP8](https://huggingface.co/unsloth/Qwen3-32B-FP8) |
515
+ | | 235B-A22B | [FP8](https://huggingface.co/unsloth/Qwen3-235B-A22B-FP8) |
516
+ | **Qwen3 (2507)** | 4B Instruct | [FP8](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-FP8) |
517
+ | | 4B Thinking | [FP8](https://huggingface.co/unsloth/Qwen3-4B-Thinking-2507-FP8) |
518
+ | | 30B-A3B Instruct | [FP8](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-FP8) |
519
+ | | 30B-A3B Thinking | [FP8](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-FP8) |
520
+ | | 235B-A22B Instruct | [FP8](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-FP8) |
521
+ | | 235B-A22B Thinking | [FP8](https://huggingface.co/unsloth/Qwen3-235B-A22B-Thinking-2507-FP8) |
522
+ | **Qwen3-VL** | 4B Instruct | [FP8](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-FP8) |
523
+ | | 4B Thinking | [FP8](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-FP8) |
524
+ | | 8B Instruct | [FP8](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-FP8) |
525
+ | | 8B Thinking | [FP8](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-FP8) |
526
+ | **Qwen3-Coder** | 480B-A35B Instruct | [FP8](https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-FP8) |
527
+ | **Granite 4.0** | h-tiny | [FP8 Dynamic](https://huggingface.co/unsloth/granite-4.0-h-tiny-FP8-Dynamic) |
528
+ | | h-small | [FP8 Dynamic](https://huggingface.co/unsloth/granite-4.0-h-small-FP8-Dynamic) |
529
+ | **Magistral Small** | 2509 | [FP8 Dynamic](https://huggingface.co/unsloth/Magistral-Small-2509-FP8-Dynamic) · [FP8 torchao](https://huggingface.co/unsloth/Magistral-Small-2509-FP8-torchao) |
530
+ | **Mistral Small 3.2** | 24B Instruct-2506 | [FP8](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8) |
531
+ | **Gemma 3** | <p>270M-it torchao<br>270m — <a href="https://huggingface.co/unsloth/gemma-3-270m-it-FP8-Dynamic">FP8</a><br>1B — <a href="https://huggingface.co/unsloth/gemma-3-1b-it-FP8-Dynamic">FP8</a><br>4B — <a href="https://huggingface.co/unsloth/gemma-3-4b-it-FP8-Dynamic">FP8</a><br>12B — <a href="https://huggingface.co/unsloth/gemma-3-12B-it-FP8-Dynamic">FP8</a><br>27B — <a href="https://huggingface.co/unsloth/gemma-3-27b-it-FP8-Dynamic">FP8</a></p> | [F](https://huggingface.co/unsloth/gemma-3-270m-it-torchao-FP8) |
532
+ | {% endtab %} | | |