@bendyline/gilde 0.1.38 → 0.1.40

package/authoring/chat-models/muse-glimmer-30b-q4.json

@@ -16,8 +16,8 @@
     "name": "Meta Superintelligence Labs",
     "url": "https://huggingface.co/meta-models/Muse-Glimmer-30B"
   },
-  "version": "1.0.1",
-  "updatedAt": "2026-08-15T00:00:00Z",
+  "version": "1.0.2",
+  "updatedAt": "2026-08-23T00:00:00Z",
   "license": "Apache-2.0",
   "licenseClass": "open",
   "licenseShortName": "Apache 2.0",
@@ -119,7 +119,7 @@
   "llamaCpp": {
     "huggingfaceRepo": "meta-models/Muse-Glimmer-30B-GGUF",
     "filename": "muse-glimmer-30B-kquant-17gb.gguf",
-    "quantization": "K-Quant-17GB",
+    "quantization": "Q4_K_M",
     "mmprojFilename": "mmproj-kquant.gguf"
   }
 }

package/authoring/chat-models/ornith-9b-q4.json

@@ -1,6 +1,6 @@
 {
   "id": "ornith-9b-q4",
-  "name": "Ornith 1.0 (9B)",
+  "name": "Ornith 1.0 (9B, Q4)",
   "description": "DeepReinforce's Ornith 1.0 at 9B parameters — an agentic-coding model built for hands-on software work. Native reasoning, native tool calling, 256K context. The small-tier pick for tool-heavy work on a 12GB+ inference budget. MIT licensed.",
   "tags": [
     "deepreinforce",

package/authoring/chat-models/ornith1.5-9b-q4.json

@@ -0,0 +1,149 @@
+{
+  "id": "ornith1.5-9b-q4",
+  "name": "Ornith 1.5 (9B, Q4)",
+  "description": "Ornith AI's dense 9B Ornith 1.5 model — a compact self-improving agentic coder trained for software engineering, tool use, and reasoning. The 4-bit build offers the practical small-tier balance of quality and memory use, with native tool calling and a 256K context window. MIT licensed; best suited to machines with 12GB+ usable memory.",
+  "tags": [
+    "ornith",
+    "coding",
+    "agentic",
+    "tools",
+    "reasoning",
+    "long-context"
+  ],
+  "category": "coding",
+  "maintainer": {
+    "name": "Ornith AI",
+    "url": "https://huggingface.co/ornith-ai"
+  },
+  "version": "1.0.0",
+  "updatedAt": "2026-08-23T00:00:00Z",
+  "versionMinGezelVersion": "1.26227",
+  "license": "MIT",
+  "licenseClass": "open",
+  "licenseShortName": "MIT",
+  "parameterSize": "9B",
+  "approxSizeBytes": 5629108992,
+  "supportsTools": true,
+  "contextWindow": 262144,
+  "upstream": "https://huggingface.co/ornith-ai/Ornith-1.5-9B",
+  "style": {
+    "family": "qwen",
+    "reasoningFormat": "think",
+    "toolCallFormat": "function-call"
+  },
+  "behaviors": [
+    "reasoning.strip-think-tags",
+    "prompt.private-reasoning-guidance",
+    "prompt.tool-cookbook-condensed",
+    "fabrication.detect-past-tense-no-tools",
+    "turn.ollama-num-predict-bumped",
+    "turn.preamble-folding",
+    "turn.ramble-detection",
+    "mcp.compact-tool-schemas",
+    "mcp.relax-required-fields",
+    "mcp.default-missing-fields",
+    "prompt.retrieval-first",
+    "tools.mlx-grammar"
+  ],
+  "tuning": {
+    "sampling": {
+      "temperature": 0.6,
+      "topP": 0.95,
+      "topK": 20,
+      "minP": 0,
+      "repetitionPenalty": 1,
+      "maxTokens": 8192
+    },
+    "samplingWhenThinking": {
+      "temperature": 0.6,
+      "topP": 0.95
+    },
+    "reasoning": {
+      "enableThinking": true,
+      "thinkingBudget": 4096
+    },
+    "promptTags": {
+      "enableThinkingTag": "/think",
+      "disableThinkingTag": "/no_think"
+    },
+    "profiles": {
+      "thinking-general": {
+        "sampling": {
+          "temperature": 0.6,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "repetitionPenalty": 1,
+          "maxTokens": 12288
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096
+        }
+      },
+      "thinking-coding": {
+        "sampling": {
+          "temperature": 0.6,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "repetitionPenalty": 1,
+          "maxTokens": 16384
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096
+        }
+      },
+      "thinking-precise": {
+        "sampling": {
+          "temperature": 0.4,
+          "topP": 0.9,
+          "topK": 20,
+          "minP": 0,
+          "repetitionPenalty": 1,
+          "seed": 0,
+          "maxTokens": 6144
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096
+        }
+      },
+      "instruct": {
+        "sampling": {
+          "temperature": 0.7,
+          "topP": 0.8,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 1.5,
+          "repetitionPenalty": 1,
+          "maxTokens": 4096
+        },
+        "reasoning": {
+          "enableThinking": false
+        }
+      },
+      "creative": {
+        "sampling": {
+          "temperature": 1.1,
+          "topP": 0.95,
+          "topK": 40,
+          "maxTokens": 8192
+        },
+        "reasoning": {
+          "enableThinking": false
+        }
+      }
+    }
+  },
+  "llamaCpp": {
+    "huggingfaceRepo": "ornith-ai/Ornith-1.5-9B-GGUF",
+    "filename": "Ornith-1.5-9B-Q4_K_M.gguf",
+    "quantization": "Q4_K_M"
+  },
+  "mlx": {
+    "huggingfaceRepo": "ornith-ai/Ornith-1.5-9B-MLX-4bit",
+    "quantization": "4bit"
+  }
+}

package/authoring/chat-models/qwen3.8-27b-iq1-s.json

@@ -0,0 +1,190 @@
+{
+  "id": "qwen3.8-27b-iq1-s",
+  "name": "Qwen 3.8 (27B, IQ1_S)",
+  "description": "Alibaba's Qwen 3.8 at 27B parameters: a dense, multimodal agentic model with native text, image, and video understanding, 262K context, flexible reasoning effort, MTP, and native tool calling. Unsloth's dynamic UD-IQ1_S is an extreme-compression build at just over 6GB, making the 27B accessible on machines with 16GB usable memory while trading more fidelity than the Q2 build for the smaller footprint.",
+  "tags": [
+    "alibaba",
+    "agentic",
+    "coding",
+    "multimodal",
+    "vision",
+    "video",
+    "tools",
+    "reasoning",
+    "long-context",
+    "low-memory"
+  ],
+  "category": "general",
+  "maintainer": {
+    "name": "Alibaba",
+    "url": "https://huggingface.co/Qwen/Qwen3.8-27B"
+  },
+  "version": "1.0.0",
+  "updatedAt": "2026-08-23T00:00:00Z",
+  "license": "Apache-2.0",
+  "licenseClass": "open",
+  "licenseShortName": "Apache 2.0",
+  "recoScore": 20,
+  "parameterSize": "27B",
+  "approxSizeBytes": 6192222208,
+  "supportsTools": true,
+  "contextWindow": 262144,
+  "upstream": "https://huggingface.co/Qwen/Qwen3.8-27B",
+  "style": {
+    "family": "qwen",
+    "reasoningFormat": "think",
+    "toolCallFormat": "function-call"
+  },
+  "behaviors": [
+    "reasoning.strip-think-tags",
+    "provider.merge-system-messages",
+    "mcp.compact-tool-schemas",
+    "provider.compact-write-transcript",
+    "fabrication.detect-past-tense-no-tools",
+    "turn.ollama-num-predict-bumped",
+    "turn.preamble-folding",
+    "turn.ramble-detection",
+    "tools.mlx-grammar",
+    "prompt.retrieval-first",
+    "prompt.workspace-gestalt",
+    "prompt.derive-by-execution"
+  ],
+  "tuning": {
+    "sampling": {
+      "temperature": 1,
+      "topP": 0.95,
+      "topK": 20,
+      "minP": 0,
+      "presencePenalty": 0,
+      "repetitionPenalty": 1,
+      "maxTokens": 12288
+    },
+    "samplingWhenThinking": {
+      "temperature": 1,
+      "topP": 0.95
+    },
+    "reasoning": {
+      "enableThinking": true,
+      "thinkingBudget": 4096,
+      "templateKwargs": {
+        "reasoning_effort": "medium"
+      }
+    },
+    "promptTags": {
+      "enableThinkingTag": "/think",
+      "disableThinkingTag": "/no_think"
+    },
+    "profiles": {
+      "thinking-general": {
+        "sampling": {
+          "temperature": 1,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 0,
+          "repetitionPenalty": 1,
+          "maxTokens": 12288
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "medium"
+          }
+        }
+      },
+      "thinking-deep": {
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "xhigh"
+          }
+        }
+      },
+      "thinking-coding": {
+        "sampling": {
+          "temperature": 1,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 0,
+          "repetitionPenalty": 1,
+          "maxTokens": 16384
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "medium"
+          }
+        }
+      },
+      "thinking-precise": {
+        "sampling": {
+          "temperature": 0.6,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 0,
+          "repetitionPenalty": 1,
+          "seed": 0,
+          "maxTokens": 6144
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "medium"
+          }
+        }
+      },
+      "instruct": {
+        "sampling": {
+          "temperature": 0.7,
+          "topP": 0.8,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 1.5,
+          "repetitionPenalty": 1,
+          "maxTokens": 4096
+        },
+        "reasoning": {
+          "enableThinking": false
+        }
+      },
+      "creative": {
+        "sampling": {
+          "temperature": 1,
+          "topP": 0.95,
+          "topK": 40,
+          "minP": 0,
+          "presencePenalty": 1.5,
+          "repetitionPenalty": 1,
+          "maxTokens": 8192
+        },
+        "reasoning": {
+          "enableThinking": false
+        }
+      }
+    }
+  },
+  "llamaCpp": {
+    "huggingfaceRepo": "unsloth/Qwen3.8-27B-GGUF",
+    "filename": "Qwen3.8-27B-UD-IQ1_S.gguf",
+    "quantization": "UD-IQ1_S",
+    "mmprojFilename": "mmproj-F16.gguf"
+  },
+  "releasePatch": {
+    "tuning": {
+      "engine": {
+        "llamaCpp": {
+          "spec": {
+            "mtp": true,
+            "nMax": 4
+          }
+        }
+      }
+    }
+  }
+}

package/authoring/chat-models/qwen3.8-27b-q2.json

@@ -0,0 +1,189 @@
+{
+  "id": "qwen3.8-27b-q2",
+  "name": "Qwen 3.8 (27B, Q2)",
+  "description": "Alibaba's Qwen 3.8 at 27B parameters: a dense, multimodal agentic model with native text, image, and video understanding, 262K context, flexible reasoning effort, MTP, and native tool calling. Unsloth's dynamic UD-Q2_K_XL brings the 27B within reach of machines with 16GB+ usable memory while retaining more fidelity than the extreme IQ1_S build.",
+  "tags": [
+    "alibaba",
+    "agentic",
+    "coding",
+    "multimodal",
+    "vision",
+    "video",
+    "tools",
+    "reasoning",
+    "long-context"
+  ],
+  "category": "general",
+  "maintainer": {
+    "name": "Alibaba",
+    "url": "https://huggingface.co/Qwen/Qwen3.8-27B"
+  },
+  "version": "1.0.0",
+  "updatedAt": "2026-08-23T00:00:00Z",
+  "license": "Apache-2.0",
+  "licenseClass": "open",
+  "licenseShortName": "Apache 2.0",
+  "recoScore": 20,
+  "parameterSize": "27B",
+  "approxSizeBytes": 9828981664,
+  "supportsTools": true,
+  "contextWindow": 262144,
+  "upstream": "https://huggingface.co/Qwen/Qwen3.8-27B",
+  "style": {
+    "family": "qwen",
+    "reasoningFormat": "think",
+    "toolCallFormat": "function-call"
+  },
+  "behaviors": [
+    "reasoning.strip-think-tags",
+    "provider.merge-system-messages",
+    "mcp.compact-tool-schemas",
+    "provider.compact-write-transcript",
+    "fabrication.detect-past-tense-no-tools",
+    "turn.ollama-num-predict-bumped",
+    "turn.preamble-folding",
+    "turn.ramble-detection",
+    "tools.mlx-grammar",
+    "prompt.retrieval-first",
+    "prompt.workspace-gestalt",
+    "prompt.derive-by-execution"
+  ],
+  "tuning": {
+    "sampling": {
+      "temperature": 1,
+      "topP": 0.95,
+      "topK": 20,
+      "minP": 0,
+      "presencePenalty": 0,
+      "repetitionPenalty": 1,
+      "maxTokens": 12288
+    },
+    "samplingWhenThinking": {
+      "temperature": 1,
+      "topP": 0.95
+    },
+    "reasoning": {
+      "enableThinking": true,
+      "thinkingBudget": 4096,
+      "templateKwargs": {
+        "reasoning_effort": "medium"
+      }
+    },
+    "promptTags": {
+      "enableThinkingTag": "/think",
+      "disableThinkingTag": "/no_think"
+    },
+    "profiles": {
+      "thinking-general": {
+        "sampling": {
+          "temperature": 1,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 0,
+          "repetitionPenalty": 1,
+          "maxTokens": 12288
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "medium"
+          }
+        }
+      },
+      "thinking-deep": {
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "xhigh"
+          }
+        }
+      },
+      "thinking-coding": {
+        "sampling": {
+          "temperature": 1,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 0,
+          "repetitionPenalty": 1,
+          "maxTokens": 16384
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "medium"
+          }
+        }
+      },
+      "thinking-precise": {
+        "sampling": {
+          "temperature": 0.6,
+          "topP": 0.95,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 0,
+          "repetitionPenalty": 1,
+          "seed": 0,
+          "maxTokens": 6144
+        },
+        "reasoning": {
+          "enableThinking": true,
+          "thinkingBudget": 4096,
+          "templateKwargs": {
+            "reasoning_effort": "medium"
+          }
+        }
+      },
+      "instruct": {
+        "sampling": {
+          "temperature": 0.7,
+          "topP": 0.8,
+          "topK": 20,
+          "minP": 0,
+          "presencePenalty": 1.5,
+          "repetitionPenalty": 1,
+          "maxTokens": 4096
+        },
+        "reasoning": {
+          "enableThinking": false
+        }
+      },
+      "creative": {
+        "sampling": {
+          "temperature": 1,
+          "topP": 0.95,
+          "topK": 40,
+          "minP": 0,
+          "presencePenalty": 1.5,
+          "repetitionPenalty": 1,
+          "maxTokens": 8192
+        },
+        "reasoning": {
+          "enableThinking": false
+        }
+      }
+    }
+  },
+  "llamaCpp": {
+    "huggingfaceRepo": "unsloth/Qwen3.8-27B-GGUF",
+    "filename": "Qwen3.8-27B-UD-Q2_K_XL.gguf",
+    "quantization": "UD-Q2_K_XL",
+    "mmprojFilename": "mmproj-F16.gguf"
+  },
+  "releasePatch": {
+    "tuning": {
+      "engine": {
+        "llamaCpp": {
+          "spec": {
+            "mtp": true,
+            "nMax": 4
+          }
+        }
+      }
+    }
+  }
+}