xinference 1.5.1__py3-none-any.whl → 1.6.0__py3-none-any.whl

xinference/model/llm/llm_family.json

@@ -6246,6 +6246,17 @@
         ],
         "model_id": "mlx-community/Qwen2.5-VL-7B-Instruct-{quantization}"
       },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen2.5-VL-32B-Instruct-{quantization}"
+      },
       {
         "model_format": "mlx",
         "model_size_in_billions": 72,
@@ -6285,6 +6296,14 @@
     ],
     "model_description": "Qwen2.5-Omni: the new flagship end-to-end multimodal model in the Qwen series.",
     "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 3,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-Omni-3B"
+      },
       {
         "model_format": "pytorch",
         "model_size_in_billions": 7,
@@ -7741,6 +7760,236 @@
       "<|im_end|>"
     ]
   },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "HuatuoGPT-o1-Qwen2.5",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "HuatuoGPT-o1 is a medical LLM designed for advanced medical reasoning. It generates a complex thought process, reflecting and refining its reasoning, before providing a final response.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "FreedomIntelligence/HuatuoGPT-o1-7B"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "FreedomIntelligence/HuatuoGPT-o1-72B"
+      }
+    ],
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "stop_token_ids": [
+      151643,
+      151644,
+      151645
+    ],
+    "stop": [
+      "<|endoftext|>",
+      "<|im_start|>",
+      "<|im_end|>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 131072,
+    "model_name": "HuatuoGPT-o1-LLaMA-3.1",
+    "model_lang": [
+      "en"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "HuatuoGPT-o1 is a medical LLM designed for advanced medical reasoning. It generates a complex thought process, reflecting and refining its reasoning, before providing a final response.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 8,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "FreedomIntelligence/HuatuoGPT-o1-8B"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 70,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "FreedomIntelligence/HuatuoGPT-o1-70B"
+      }
+    ],
+    "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+    "stop_token_ids": [
+      128001,
+      128008,
+      128009
+    ],
+    "stop": [
+      "<|end_of_text|>",
+      "<|eot_id|>",
+      "<|eom_id|>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "DianJin-R1",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "Tongyi DianJin is a financial intelligence solution platform built by Alibaba Cloud, dedicated to providing financial business developers with a convenient artificial intelligence application development environment.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "DianJin/DianJin-R1-7B"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "DianJin/DianJin-R1-32B"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "Q2_K",
+          "Q3_K_S",
+          "Q3_K_M",
+          "Q3_K_L",
+          "IQ4_XS",
+          "Q4_K_S",
+          "Q4_K_M",
+          "Q5_K_S",
+          "Q5_K_M",
+          "Q6_K",
+          "Q8_0",
+          "f16"
+        ],
+        "model_id": "mradermacher/DianJin-R1-7B-GGUF",
+        "model_file_name_template": "DianJin-R1-7B.{quantization}.gguf"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "i1-IQ1_S",
+          "i1-IQ1_M",
+          "i1-IQ2_XXS",
+          "i1-IQ2_XS",
+          "i1-IQ2_S",
+          "i1-IQ2_M",
+          "i1-Q2_K_S",
+          "i1-Q2_K",
+          "i1-IQ3_XXS",
+          "i1-IQ3_XS",
+          "i1-Q3_K_S",
+          "i1-IQ3_S",
+          "i1-IQ3_M",
+          "i1-Q3_K_M",
+          "i1-Q3_K_L",
+          "i1-IQ4_XS",
+          "i1-IQ4_NL",
+          "i1-Q4_0",
+          "i1-Q4_K_S",
+          "i1-Q4_K_M",
+          "i1-Q4_1",
+          "i1-Q5_K_S",
+          "i1-Q5_K_M",
+          "i1-Q6_K"
+        ],
+        "model_id": "mradermacher/DianJin-R1-7B-i1-GGUF",
+        "model_file_name_template": "DianJin-R1-7B.{quantization}.gguf"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "Q2_K",
+          "Q3_K_S",
+          "Q3_K_M",
+          "Q3_K_L",
+          "IQ4_XS",
+          "Q4_K_S",
+          "Q4_K_M",
+          "Q5_K_S",
+          "Q5_K_M",
+          "Q6_K",
+          "Q8_0"
+        ],
+        "model_id": "mradermacher/DianJin-R1-32B-GGUF",
+        "model_file_name_template": "DianJin-R1-32B.{quantization}.gguf"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "i1-IQ1_S",
+          "i1-IQ1_M",
+          "i1-IQ2_XXS",
+          "i1-IQ2_XS",
+          "i1-IQ2_S",
+          "i1-IQ2_M",
+          "i1-Q2_K_S",
+          "i1-Q2_K",
+          "i1-IQ3_XXS",
+          "i1-IQ3_XS",
+          "i1-Q3_K_S",
+          "i1-IQ3_S",
+          "i1-IQ3_M",
+          "i1-Q3_K_M",
+          "i1-Q3_K_L",
+          "i1-IQ4_XS",
+          "i1-Q4_0",
+          "i1-Q4_K_S",
+          "i1-Q4_K_M",
+          "i1-Q4_1",
+          "i1-Q5_K_S",
+          "i1-Q5_K_M",
+          "i1-Q6_K"
+        ],
+        "model_id": "mradermacher/DianJin-R1-32B-i1-GGUF",
+        "model_file_name_template": "DianJin-R1-32B.{quantization}.gguf"
+      }
+    ],
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "stop_token_ids": [
+      151643,
+      151644,
+      151645
+    ],
+    "stop": [
+      "<|endoftext|>",
+      "<|im_start|>",
+      "<|im_end|>"
+    ]
+  },
   {
     "version": 1,
     "context_length": 32768,
@@ -8041,6 +8290,49 @@
       "<|im_end|>"
     ]
   },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "XiYanSQL-QwenCoder-2504",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "The XiYanSQL-QwenCoder models, as multi-dialect SQL base models, demonstrating robust SQL generation capabilities.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "XGenerationLab/XiYanSQL-QwenCoder-7B-2504"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "XGenerationLab/XiYanSQL-QwenCoder-32B-2504"
+      }
+    ],
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "stop_token_ids": [
+      151643,
+      151644,
+      151645
+    ],
+    "stop": [
+      "<|endoftext|>",
+      "<|im_start|>",
+      "<|im_end|>"
+    ]
+  },
   {
     "version": 1,
     "context_length": 32768,
@@ -8166,37 +8458,40 @@
         "model_format": "ggufv2",
         "model_size_in_billions": 32,
         "quantizations": [
-          "fp16",
-          "q4_k_m",
-          "q5_0",
-          "q5_k_m",
-          "q6_k",
-          "q8_0"
+          "BF16",
+          "IQ4_NL",
+          "IQ4_XS",
+          "Q2_K",
+          "Q2_K_L",
+          "Q3_K_M",
+          "Q3_K_S",
+          "Q4_0",
+          "Q4_1",
+          "Q4_K_M",
+          "Q5_K_M",
+          "Q6_K",
+          "UD-IQ1_M",
+          "UD-IQ1_S",
+          "UD-IQ2_M",
+          "UD-IQ2_XXS",
+          "UD-IQ3_XXS",
+          "UD-Q2_K_XL",
+          "UD-Q3_K_XL",
+          "UD-Q4_K_XL",
+          "UD-Q5_K_XL",
+          "UD-Q6_K_XL",
+          "UD-Q8_K_XL",
+          "Q8_0"
         ],
         "quantization_parts": {
-          "fp16": [
-            "00001-of-00017",
-            "00002-of-00017",
-            "00003-of-00017",
-            "00004-of-00017",
-            "00005-of-00017",
-            "00006-of-00017",
-            "00007-of-00017",
-            "00008-of-00017",
-            "00009-of-00017",
-            "00010-of-00017",
-            "00011-of-00017",
-            "00012-of-00017",
-            "00013-of-00017",
-            "00014-of-00017",
-            "00015-of-00017",
-            "00016-of-00017",
-            "00017-of-00017"
+          "BF16": [
+            "00001-of-00002",
+            "00002-of-00002"
           ]
         },
-        "model_id": "Qwen/QwQ-32B-GGUF",
-        "model_file_name_template": "qwq-32b-{quantization}.gguf",
-        "model_file_name_split_template": "fp16/qwq-32b-{quantization}-{part}.gguf"
+        "model_id": "unsloth/QwQ-32B-GGUF",
+        "model_file_name_template": "QwQ-32B-{quantization}.gguf",
+        "model_file_name_split_template": "BF16/QwQ-32B-{quantization}-{part}.gguf"
       }
     ],
     "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n  {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" and not message.tool_calls %}\n        {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
@@ -9140,6 +9435,7 @@
       {
         "model_format": "pytorch",
         "model_size_in_billions": 27,
+        "activated_size_in_billions": "4_5",
         "quantizations": [
           "none"
         ],
@@ -9148,6 +9444,7 @@
       {
         "model_format": "pytorch",
         "model_size_in_billions": 16,
+        "activated_size_in_billions": "2_8",
         "quantizations": [
           "none"
         ],
@@ -9156,6 +9453,7 @@
       {
         "model_format": "pytorch",
         "model_size_in_billions": 3,
+        "activated_size_in_billions": 1,
         "quantizations": [
           "none"
         ],
@@ -9271,7 +9569,7 @@
         ],
         "model_id": "mlx-community/GLM-4-32B-0414-{quantization}"
       },
-       {
+      {
         "model_format": "ggufv2",
         "model_size_in_billions": 9,
         "quantizations": [
@@ -9357,110 +9655,110 @@
     }
   },
   {
-    "version":1,
-    "context_length":32768,
-    "model_name":"Ovis2",
-    "model_lang":[
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "Ovis2",
+    "model_lang": [
       "en",
       "zh"
     ],
-    "model_ability":[
+    "model_ability": [
       "chat",
       "vision"
     ],
-    "model_description":"Ovis (Open VISion) is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.",
-    "model_specs":[
+    "model_description": "Ovis (Open VISion) is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.",
+    "model_specs": [
       {
-        "model_format":"pytorch",
-        "model_size_in_billions":1,
-        "quantizations":[
+        "model_format": "pytorch",
+        "model_size_in_billions": 1,
+        "quantizations": [
           "none"
         ],
-        "model_id":"AIDC-AI/Ovis2-1B"
+        "model_id": "AIDC-AI/Ovis2-1B"
       },
       {
-        "model_format":"pytorch",
-        "model_size_in_billions":2,
-        "quantizations":[
+        "model_format": "pytorch",
+        "model_size_in_billions": 2,
+        "quantizations": [
           "none"
         ],
-        "model_id":"AIDC-AI/Ovis2-2B"
+        "model_id": "AIDC-AI/Ovis2-2B"
       },
       {
-        "model_format":"pytorch",
-        "model_size_in_billions":4,
-        "quantizations":[
+        "model_format": "pytorch",
+        "model_size_in_billions": 4,
+        "quantizations": [
           "none"
         ],
-        "model_id":"AIDC-AI/Ovis2-4B"
+        "model_id": "AIDC-AI/Ovis2-4B"
       },
       {
-        "model_format":"pytorch",
-        "model_size_in_billions":8,
-        "quantizations":[
+        "model_format": "pytorch",
+        "model_size_in_billions": 8,
+        "quantizations": [
           "none"
         ],
-        "model_id":"AIDC-AI/Ovis2-8B"
+        "model_id": "AIDC-AI/Ovis2-8B"
       },
       {
-        "model_format":"pytorch",
-        "model_size_in_billions":16,
-        "quantizations":[
+        "model_format": "pytorch",
+        "model_size_in_billions": 16,
+        "quantizations": [
           "none"
         ],
-        "model_id":"AIDC-AI/Ovis2-16B"
+        "model_id": "AIDC-AI/Ovis2-16B"
       },
       {
-        "model_format":"pytorch",
-        "model_size_in_billions":34,
-        "quantizations":[
+        "model_format": "pytorch",
+        "model_size_in_billions": 34,
+        "quantizations": [
           "none"
         ],
-        "model_id":"AIDC-AI/Ovis2-34B"
+        "model_id": "AIDC-AI/Ovis2-34B"
       },
       {
-        "model_format":"gptq",
-        "model_size_in_billions":2,
-        "quantizations":[
+        "model_format": "gptq",
+        "model_size_in_billions": 2,
+        "quantizations": [
           "Int4"
         ],
-        "model_id":"AIDC-AI/Ovis2-2B-GPTQ-{quantization}"
+        "model_id": "AIDC-AI/Ovis2-2B-GPTQ-{quantization}"
       },
       {
-        "model_format":"gptq",
-        "model_size_in_billions":4,
-        "quantizations":[
+        "model_format": "gptq",
+        "model_size_in_billions": 4,
+        "quantizations": [
           "Int4"
         ],
-        "model_id":"AIDC-AI/Ovis2-4B-GPTQ-{quantization}"
+        "model_id": "AIDC-AI/Ovis2-4B-GPTQ-{quantization}"
       },
       {
-        "model_format":"gptq",
-        "model_size_in_billions":8,
-        "quantizations":[
+        "model_format": "gptq",
+        "model_size_in_billions": 8,
+        "quantizations": [
           "Int4"
         ],
-        "model_id":"AIDC-AI/Ovis2-8B-GPTQ-{quantization}"
+        "model_id": "AIDC-AI/Ovis2-8B-GPTQ-{quantization}"
       },
       {
-        "model_format":"gptq",
-        "model_size_in_billions":16,
-        "quantizations":[
+        "model_format": "gptq",
+        "model_size_in_billions": 16,
+        "quantizations": [
           "Int4"
         ],
-        "model_id":"AIDC-AI/Ovis2-16B-GPTQ-{quantization}"
+        "model_id": "AIDC-AI/Ovis2-16B-GPTQ-{quantization}"
       },
       {
-        "model_format":"gptq",
-        "model_size_in_billions":34,
-        "quantizations":[
+        "model_format": "gptq",
+        "model_size_in_billions": 34,
+        "quantizations": [
           "Int4",
           "Int8"
         ],
-        "model_id":"AIDC-AI/Ovis2-34B-GPTQ-{quantization}"
+        "model_id": "AIDC-AI/Ovis2-34B-GPTQ-{quantization}"
       }
     ],
-    "chat_template":  "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
     "stop_token_ids": [
       151645,
       151643
@@ -9587,6 +9885,64 @@
       "<|im_end|>"
     ]
   },
+  {
+    "version": 1,
+    "context_length": 131072,
+    "model_name": "skywork-or1",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat"
+    ],
+    "model_description": "We release the final version of Skywork-OR1 (Open Reasoner 1) series of models, including",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "Skywork/Skywork-OR1-32B"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "Int8",
+          "Int4"
+        ],
+        "model_id": "JunHowie/Skywork-OR1-32B-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "Skywork/Skywork-OR1-7B"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "Int8",
+          "Int4"
+        ],
+        "model_id": "JunHowie/Skywork-OR1-7B-GPTQ-{quantization}"
+      }
+    ],
+    "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+    "stop_token_ids": [
+      151643
+    ],
+    "stop": [
+      "<｜end▁of▁sentence｜>"
+    ],
+    "reasoning_start_tag": "<think>",
+    "reasoning_end_tag": "</think>"
+  },
   {
     "version": 1,
     "context_length": 40960,
@@ -9598,6 +9954,7 @@
     "model_ability": [
       "chat",
       "reasoning",
+      "hybrid",
       "tools"
     ],
     "model_description": "Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support",
@@ -9622,10 +9979,29 @@
         "model_format": "gptq",
         "model_size_in_billions": "0_6",
         "quantizations": [
-          "Int4",
           "Int8"
         ],
-        "model_id": "JunHowie/Qwen3-0.6B-GPTQ-{quantization}"
+        "model_id": "Qwen/Qwen3-0.6B-GPTQ-Int8"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": "0_6",
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "JunHowie/Qwen3-0.6B-GPTQ-Int4"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": "0_6",
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen3-0.6B-{quantization}"
       },
       {
         "model_format": "ggufv2",
@@ -9679,10 +10055,29 @@
         "model_format": "gptq",
         "model_size_in_billions": "1_7",
         "quantizations": [
-          "Int4",
           "Int8"
         ],
-        "model_id": "JunHowie/Qwen3-1.7B-GPTQ-{quantization}"
+        "model_id": "Qwen/Qwen3-1.7B-GPTQ-Int8"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": "1_7",
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "JunHowie/Qwen3-1.7B-GPTQ-Int4"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": "1_7",
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen3-1.7B-{quantization}"
       },
       {
         "model_format": "ggufv2",
@@ -9732,6 +10127,14 @@
         ],
         "model_id": "Qwen/Qwen3-4B-FP8"
       },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 4,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen3-4B-AWQ"
+      },
       {
         "model_format": "gptq",
         "model_size_in_billions": 4,
@@ -9741,6 +10144,18 @@
         ],
         "model_id": "JunHowie/Qwen3-4B-GPTQ-{quantization}"
       },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 4,
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen3-4B-{quantization}"
+      },
       {
         "model_format": "ggufv2",
         "model_size_in_billions": 4,
@@ -9789,6 +10204,14 @@
         ],
         "model_id": "Qwen/Qwen3-8B-FP8"
       },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 8,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen3-8B-AWQ"
+      },
       {
         "model_format": "gptq",
         "model_size_in_billions": 8,
@@ -9798,6 +10221,18 @@
         ],
         "model_id": "JunHowie/Qwen3-8B-GPTQ-{quantization}"
       },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 8,
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen3-8B-{quantization}"
+      },
       {
         "model_format": "ggufv2",
         "model_size_in_billions": 8,
@@ -9846,6 +10281,14 @@
         ],
         "model_id": "Qwen/Qwen3-14B-FP8"
       },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen3-14B-AWQ"
+      },
       {
         "model_format": "gptq",
         "model_size_in_billions": 14,
@@ -9855,6 +10298,18 @@
         ],
         "model_id": "JunHowie/Qwen3-14B-GPTQ-{quantization}"
       },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen3-14B-{quantization}"
+      },
       {
         "model_format": "ggufv2",
         "model_size_in_billions": 14,
@@ -9910,10 +10365,30 @@
         "model_size_in_billions": 30,
         "activated_size_in_billions": 3,
         "quantizations": [
-          "Int4",
           "Int8"
         ],
-        "model_id": "JunHowie/Qwen3-30B-A3B-GPTQ-{quantization}"
+        "model_id": "JunHowie/Qwen3-30B-A3B-GPTQ-Int8"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 30,
+        "activated_size_in_billions": 3,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen3-30B-A3B-GPTQ-Int4"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 30,
+        "activated_size_in_billions": 3,
+        "quantizations": [
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen3-30B-A3B-{quantization}"
       },
       {
         "model_format": "ggufv2",
@@ -9971,7 +10446,15 @@
         ],
         "model_id": "Qwen/Qwen3-32B-FP8"
       },
-       {
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen3-32B-AWQ"
+      },
+      {
         "model_format": "gptq",
         "model_size_in_billions": 32,
         "quantizations": [
@@ -9980,6 +10463,17 @@
         ],
         "model_id": "JunHowie/Qwen3-32B-GPTQ-{quantization}"
       },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/Qwen3-32B-{quantization}"
+      },
       {
         "model_format": "ggufv2",
         "model_size_in_billions": 32,
@@ -10026,7 +10520,7 @@
         "quantizations": [
           "none"
         ],
-        "model_id": "Qwen/Qwen3-235B"
+        "model_id": "Qwen/Qwen3-235B-A22B"
       },
       {
         "model_format": "fp8",
@@ -10035,7 +10529,36 @@
         "quantizations": [
           "fp8"
         ],
-        "model_id": "Qwen/Qwen3-235B-FP8"
+        "model_id": "Qwen/Qwen3-235B-A22B-FP8"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 235,
+        "activated_size_in_billions": 22,
+        "quantizations": [
+          "Int8"
+        ],
+        "model_id": "QuantTrio/Qwen3-235B-A22B-GPTQ-Int8"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 235,
+        "activated_size_in_billions": 22,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen3-235B-A22B-GPTQ-Int4"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 235,
+        "activated_size_in_billions": 22,
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "8bit"
+        ],
+        "model_id": "mlx-community/Qwen/Qwen3-235B-A22B-{quantization}"
       },
       {
         "model_format": "ggufv2",
@@ -10149,6 +10672,7 @@
     "virtualenv": {
       "packages": [
         "transformers>=4.51.0",
+        "mlx-lm>=0.24.0 ; sys_platform=='darwin'",
         "numpy==1.26.4"
       ]
     }