docs/zh/SUPPORTED_MODELS.md · thu-pacman/chitu

# 支持的模型

> 本页面由脚本自动生成。数据源: `chitu/config/models/*.yaml`。更新命令: `python3 script/generate_supported_models_docs.py`。

## 开源模型

| 名称 | 支持工具调用（内含约束解码） | 用法（启动赤兔时追加下列参数） | 获取方法 |
|---|---|---|---|
| DeepSeek-R1 | ✓ | `models=DeepSeek-R1` | https://huggingface.co/deepseek-ai/DeepSeek-R1 |
| DeepSeek-R1-Distill-Llama-70B |  | `models=DeepSeek-R1-Distill-Llama-70B` | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
| DeepSeek-R1-Distill-Qwen-14B |  | `models=DeepSeek-R1-Distill-Qwen-14B` | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B |
| DeepSeek-R1-FP4 | ✓ | `models=DeepSeek-R1-FP4` | https://huggingface.co/nvidia/DeepSeek-R1-FP4 |
| DeepSeek-R1-Q4_K_M | ✓ | `models=DeepSeek-R1-Q4_K_M` | https://huggingface.co/bartowski/DeepSeek-R1-GGUF |
| DeepSeek-R1-bf16 | ✓ | `models=DeepSeek-R1-bf16` | https://huggingface.co/opensourcerelease/DeepSeek-R1-bf16 |
| DeepSeek-R1-mix-fp4 | ✓ | `models=DeepSeek-R1-fp4-all` | https://www.modelscope.cn/models/qingcheng-ai/DeepSeek-R1-fp4 |
| DeepSeek-R1-mix-fp4 | ✓ | `models=DeepSeek-R1-fp4-mix` | https://www.modelscope.cn/models/qingcheng-ai/DeepSeek-R1-mix |
| DeepSeek-V3 | ✓ | `models=DeepSeek-V3` | https://huggingface.co/deepseek-ai/DeepSeek-V3 |
| DeepSeek-V3.1 | ✓ | `models=DeepSeek-V3.1` | https://huggingface.co/deepseek-ai/DeepSeek-V3.1 |
| DeepSeek-V3.1-Terminus | ✓ | `models=DeepSeek-V3.1-Terminus` | https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus |
| DeepSeek-V3.2 | ✓ | `models=DeepSeek-V3.2` | https://huggingface.co/deepseek-ai/DeepSeek-V3.2 |
| DeepSeek-V3.2-Exp | ✓ | `models=DeepSeek-V3.2-Exp` | https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp |
| DeepSeek-V3.2-Exp-kv-fp8 | ✓ | `models=DeepSeek-V3.2-Exp-kv-fp8` | https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp |
| DeepSeek-V3.2-kv-fp8 | ✓ | `models=DeepSeek-V3.2-kv-fp8` | https://huggingface.co/deepseek-ai/DeepSeek-V3.2 |
| glm-4-32b |  | `models=GLM-4-32B-0414` | https://modelscope.cn/models/ZhipuAI/GLM-4-32B-0414 |
| glm-4-9b |  | `models=GLM-4-9B-0414` | https://www.modelscope.cn/models/ZhipuAI/GLM-4-9B-0414 |
| GLM-4.5 | ✓ | `models=GLM-4.5` | https://huggingface.co/zai-org/GLM-4.5 |
| GLM-4.5-Air | ✓ | `models=GLM-4.5-Air` | https://huggingface.co/zai-org/GLM-4.5-Air |
| GLM-4.5V |  | `models=GLM-4.5V` | https://huggingface.co/zai-org/GLM-4.5V |
| GLM-4.6 | ✓ | `models=GLM-4.6` | https://huggingface.co/zai-org/GLM-4.6 |
| GLM-4.6V |  | `models=GLM-4.6V` | https://huggingface.co/zai-org/GLM-4.6V |
| GLM-4.7 | ✓ | `models=GLM-4.7` | https://huggingface.co/zai-org/GLM-4.7 |
| GLM-4.7-FP8 | ✓ | `models=GLM-4.7-FP8` | https://huggingface.co/zai-org/GLM-4.7-FP8 |
| GLM-4.7-Flash | ✓ | `models=GLM-4.7-Flash` | https://huggingface.co/zai-org/GLM-4.7-Flash |
| GLM-5 | ✓ | `models=GLM-5` | https://huggingface.co/zai-org/GLM-5 |
| GLM-5-FP8 | ✓ | `models=GLM-5-FP8` | https://huggingface.co/zai-org/GLM-5-FP8 |
| glm-z1-32b |  | `models=GLM-Z1-32B-0414` | https://modelscope.cn/models/ZhipuAI/GLM-Z1-32B-0414/ |
| glm-z1-9b |  | `models=GLM-Z1-9B-0414` | https://modelscope.cn/models/ZhipuAI/GLM-Z1-9B-0414 |
| Kimi-K2-Instruct |  | `models=Kimi-K2-Instruct` | https://huggingface.co/moonshotai/Kimi-K2-Instruct |
| Kimi-K2.5 |  | `models=Kimi-K2.5` | https://huggingface.co/moonshotai/Kimi-K2.5 |
| Kimi-K2.6 |  | `models=Kimi-K2.6` | https://huggingface.co/moonshotai/Kimi-K2.6 |
| LLaDA2.1-flash |  | `models=LLaDA2.1-flash` | https://huggingface.co/inclusionAI/LLaDA2.0-flash |
| LLaDA2.1-mini |  | `models=LLaDA2.1-mini` | https://huggingface.co/inclusionAI/LLaDA2.0-mini |
| Llama-3-8B-QServe |  | `models=Llama-3-8B-QServe` | https://huggingface.co/mit-han-lab/Llama-3-8B-QServe |
| Llama-3-8B-QServe-g128 |  | `models=Llama-3-8B-QServe-g128` | https://huggingface.co/mit-han-lab/Llama-3-8B-QServe-g128 |
| Llama-3.3-70B-Instruct |  | `models=Llama-3.3-70B-Instruct` | https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct |
| Meta-Llama-3-8B-Instruct |  | `models=Meta-Llama-3-8B-Instruct` | https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct (The default checkpoint. Not the "original" one) |
| Meta-Llama-3-8B-Instruct-original |  | `models=Meta-Llama-3-8B-Instruct-original` | https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct (Please use its "original" checkpoint) |
| Mixtral-8x7B-Instruct-v0.1 |  | `models=Mixtral-8x7B-Instruct-v0.1` | https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 |
| QwQ-32B |  | `models=QwQ-32B` | https://huggingface.co/Qwen/QwQ-32B |
| QwQ-32B-AWQ |  | `models=QwQ-32B-AWQ` | https://huggingface.co/Qwen/QwQ-32B-AWQ |
| QwQ-32B-FP8 |  | `models=QwQ-32B-FP8` | https://huggingface.co/qingcheng-ai/QWQ-32B-FP8 |
| QwQ-32B-GPTQ |  | `models=QwQ-32B-GPTQ` | https://huggingface.co/clowman/QwQ-32B-GPTQ-Int8 |
| QwQ-32B-fp4 |  | `models=QwQ-32B-fp4` | https://huggingface.co/qingcheng-ai/QwQ-32B-fp4 |
| Qwen2-72B-Instruct |  | `models=Qwen2-72B-Instruct` | https://huggingface.co/Qwen/Qwen2-72B-Instruct |
| Qwen2-7B-Instruct |  | `models=Qwen2-7B-Instruct` | https://huggingface.co/Qwen/Qwen2-7B-Instruct |
| Qwen2.5-0.5B |  | `models=Qwen2.5-0.5B` | https://huggingface.co/Qwen/Qwen2.5-0.5B |
| Qwen2.5-0.5B-Instruct |  | `models=Qwen2.5-0.5B-Instruct` | https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct |
| Qwen2.5-1.5B |  | `models=Qwen2.5-1.5B` | https://huggingface.co/Qwen/Qwen2.5-1.5B |
| Qwen2.5-1.5B-Instruct |  | `models=Qwen2.5-1.5B-Instruct` | https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct |
| Qwen2.5-32B |  | `models=Qwen2.5-32B` | https://huggingface.co/Qwen/Qwen2.5-32B |
| Qwen2.5-32B-Instruct |  | `models=Qwen2.5-32B-Instruct` | https://huggingface.co/Qwen/Qwen2.5-32B-Instruct |
| Qwen2.5-3B |  | `models=Qwen2.5-3B` | https://huggingface.co/Qwen/Qwen2.5-3B |
| Qwen2.5-3B-Instruct |  | `models=Qwen2.5-3B-Instruct` | https://huggingface.co/Qwen/Qwen2.5-3B-Instruct |
| Qwen2.5-7B |  | `models=Qwen2.5-7B` | https://huggingface.co/Qwen/Qwen2.5-7B |
| Qwen2.5-7B-Instruct |  | `models=Qwen2.5-7B-Instruct` | https://huggingface.co/Qwen/Qwen2.5-7B-Instruct |
| Qwen2.5-VL-32B-Instruct |  | `models=Qwen2.5-VL-32B-Instruct` | https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct |
| Qwen2.5-VL-7B-Instruct |  | `models=Qwen2.5-VL-7B-Instruct` | https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct |
| Qwen3-0.6B | ✓ | `models=Qwen3-0.6B` | https://huggingface.co/Qwen/Qwen3-0.6B |
| Qwen3-1.7B | ✓ | `models=Qwen3-1.7B` | https://huggingface.co/Qwen/Qwen3-1.7B |
| Qwen3-14B | ✓ | `models=Qwen3-14B` | https://huggingface.co/Qwen/Qwen3-14B |
| Qwen3-14B-FP8 | ✓ | `models=Qwen3-14B-FP8` | https://huggingface.co/Qwen/Qwen3-14B-FP8 |
| Qwen3-235B-A22B | ✓ | `models=Qwen3-235B-A22B` | https://huggingface.co/Qwen/Qwen3-235B-A22B |
| Qwen3-235B-A22B-Instruct | ✓ | `models=Qwen3-235B-A22B-Instruct` | https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507 |
| Qwen3-235B-A22B-fp4 | ✓ | `models=Qwen3-235B-A22B-fp4` | https://huggingface.co/nvidia/Qwen3-235B-A22B-NVFP4 |
| Qwen3-235B-A22B-fp8 | ✓ | `models=Qwen3-235B-A22B-fp8` | https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8 |
| Qwen3-235B-A22B-fp8 | ✓ | `models=Qwen3-235B-A22B-fp8-kv` | https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8 |
| Qwen3-30B-A3B | ✓ | `models=Qwen3-30B-A3B` | https://huggingface.co/Qwen/Qwen3-30B-A3B |
| Qwen3-30B-A3B-fp4 | ✓ | `models=Qwen3-30B-A3B-fp4` | https://huggingface.co/nvidia/Qwen3-30B-A3B-NVFP4 |
| Qwen3-30B-A3B-fp8 | ✓ | `models=Qwen3-30B-A3B-fp8` | https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8 |
| Qwen3-30B-A3B-fp8-kv | ✓ | `models=Qwen3-30B-A3B-fp8-kv` | https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8 |
| Qwen3-32B | ✓ | `models=Qwen3-32B` | https://huggingface.co/Qwen/Qwen3-32B |
| Qwen3-32B-FP8 | ✓ | `models=Qwen3-32B-FP8` | https://huggingface.co/Qwen/Qwen3-32B-FP8 |
| Qwen3-32B-fp4 | ✓ | `models=Qwen3-32B-fp4` | https://huggingface.co/qingcheng-ai/Qwen3-32B-fp4 |
| Qwen3-4B | ✓ | `models=Qwen3-4B` | https://huggingface.co/Qwen/Qwen3-4B |
| Qwen3-8B | ✓ | `models=Qwen3-8B` | https://huggingface.co/Qwen/Qwen3-8B |
| Qwen3-8B-fp4 | ✓ | `models=Qwen3-8B-fp4` | https://huggingface.co/qingcheng-ai/Qwen3-8B-fp4 |
| Qwen3-Coder-30B-A3B-Instruct | ✓ | `models=Qwen3-Coder-30B-A3B-Instruct` | https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct |
| Qwen3-Coder-30B-A3B-Instruct-fp8 | ✓ | `models=Qwen3-Coder-30B-A3B-Instruct-fp8` | https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 |
| Qwen3-Coder-480B-A35B-Instruct | ✓ | `models=Qwen3-Coder-480B-A35B-Instruct` | https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct |
| Qwen3-Coder-480B-A35B-Instruct-fp8 | ✓ | `models=Qwen3-Coder-480B-A35B-Instruct-fp8` | https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 |
| Qwen3-Coder-Next | ✓ | `models=Qwen3-Coder-Next` | https://huggingface.co/Qwen/Qwen3-Coder-Next |
| Qwen3-Coder-Next-FP8 | ✓ | `models=Qwen3-Coder-Next-FP8` | https://huggingface.co/Qwen/Qwen3-Coder-Next-FP8 |
| Qwen3-Next-80B-A3B-Instruct | ✓ | `models=Qwen3-Next-80B-A3B-Instruct` | https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct |
| Qwen3-Next-80B-A3B-Instruct-FP8 | ✓ | `models=Qwen3-Next-80B-A3B-Instruct-FP8` | https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct-FP8 |
| Qwen3-Next-80B-A3B-Thinking | ✓ | `models=Qwen3-Next-80B-A3B-Thinking` | https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking |
| Qwen3-VL-235B-A22B-Instruct |  | `models=Qwen3-VL-235B-A22B-Instruct` | https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct |
| Qwen3-VL-8B-Instruct |  | `models=Qwen3-VL-8B-Instruct` | https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct |
| Qwen3.5-0.8B | ✓ | `models=Qwen3.5-0.8B` | https://huggingface.co/Qwen/Qwen3.5-0.8B |
| Qwen3.5-122B-A10B | ✓ | `models=Qwen3.5-122B-A10B` | https://huggingface.co/Qwen/Qwen3.5-122B-A10B |
| Qwen3.5-122B-A10B-FP8 | ✓ | `models=Qwen3.5-122B-A10B-FP8` | https://huggingface.co/Qwen/Qwen3.5-122B-A10B-FP8 |
| Qwen3.5-27B | ✓ | `models=Qwen3.5-27B` | https://huggingface.co/Qwen/Qwen3.5-27B |
| Qwen3.5-27B-FP8 | ✓ | `models=Qwen3.5-27B-FP8` | https://huggingface.co/Qwen/Qwen3.5-27B-FP8 |
| Qwen3.5-2B | ✓ | `models=Qwen3.5-2B` | https://huggingface.co/Qwen/Qwen3.5-2B |
| Qwen3.5-35B-A3B | ✓ | `models=Qwen3.5-35B-A3B` | https://huggingface.co/Qwen/Qwen3.5-35B-A3B |
| Qwen3.5-35B-A3B-FP8 | ✓ | `models=Qwen3.5-35B-A3B-FP8` | https://huggingface.co/Qwen/Qwen3.5-35B-A3B-FP8 |
| Qwen3.5-397B-A17B | ✓ | `models=Qwen3.5-397B-A17B` | https://huggingface.co/Qwen/Qwen3.5-397B-A17B |
| Qwen3.5-397B-A17B-FP8 | ✓ | `models=Qwen3.5-397B-A17B-FP8` | https://huggingface.co/Qwen/Qwen3.5-397B-A17B-FP8 |
| Qwen3.5-4B | ✓ | `models=Qwen3.5-4B` | https://huggingface.co/Qwen/Qwen3.5-4B |
| Qwen3.5-9B | ✓ | `models=Qwen3.5-9B` | https://huggingface.co/Qwen/Qwen3.5-9B |
| Qwen3.6-27B | ✓ | `models=Qwen3.6-27B` | https://huggingface.co/Qwen/Qwen3.6-27B |
| Qwen3.6-27B-FP8 | ✓ | `models=Qwen3.6-27B-FP8` | https://huggingface.co/Qwen/Qwen3.6-27B-FP8 |
| Qwen3.6-35B-A3B | ✓ | `models=Qwen3.6-35B-A3B` | https://huggingface.co/Qwen/Qwen3.6-35B-A3B |
| Qwen3.6-35B-A3B-FP8 | ✓ | `models=Qwen3.6-35B-A3B-FP8` | https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8 |
| Seed-OSS-36B-Instruct |  | `models=Seed-OSS-36B-Instruct` | https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct |
| glm-4-9b-chat |  | `models=glm-4-9b-chat` | https://huggingface.co/zai-org/glm-4-9b-chat-hf |
| gpt-oss-120b-BF16 |  | `models=gpt-oss-120b-BF16` | https://huggingface.co/unsloth/gpt-oss-120b-BF16 |
| gpt-oss-20b-BF16 |  | `models=gpt-oss-20b-BF16` | https://huggingface.co/unsloth/gpt-oss-20b-BF16 |

## 赤兔-pro 模型

以下模型随赤兔-pro提供，请联系 [solution@chitu.ai](solution@chitu.ai) 进行商务咨询。

| 名称 | 支持工具调用（内含约束解码） | 用法（启动赤兔时追加下列参数） |
|---|---|---|
| DeepSeek-R1-Distill-Llama-70B-ascend-int8 |  | `models=DeepSeek-R1-Distill-Llama-70B-ascend-int8` |
| DeepSeek-R1-Distill-Qwen-14B-fp8 |  | `models=DeepSeek-R1-Distill-Qwen-14B-fp8` |
| DeepSeek-R1-ascend-int8 | ✓ | `models=DeepSeek-R1-int8-ascend` |
| DeepSeek-R1-MXFP4 | ✓ | `models=DeepSeek-R1-mxfp4` |
| DeepSeek-V3-ascend-int8 | ✓ | `models=DeepSeek-V3-int8-ascend` |
| DeepSeek-V3.1-Terminus-ascend-int8 | ✓ | `models=DeepSeek-V3.1-Terminus-int8-ascend` |
| GLM-4.5-Air-qc-fp8 | ✓ | `models=GLM-4.5-Air-qc-fp8` |
| GLM-4.5-qc-fp8 | ✓ | `models=GLM-4.5-qc-fp8` |
| QwQ-32B-simple-w8a8 |  | `models=QwQ-32B-simple-w8a8` |
| QwQ-32B-simple-w8a8-muxi |  | `models=QwQ-32B-simple-w8a8-muxi` |
| Qwen2.5-3B-Mix |  | `models=Qwen2.5-3B-Mix` |
| Qwen2.5-72B-Instruct-ascend-int8 |  | `models=Qwen2.5-72B-Instruct-ascend-int8` |
| Qwen2.5-VL-32B-Instruct-ascend-int8 |  | `models=Qwen2.5-VL-32B-Instruct-ascend-int8` |
| Qwen3-14B-QServe-g128 | ✓ | `models=Qwen3-14B-QServe-g128` |
| Qwen3-14B-ascend-int8 | ✓ | `models=Qwen3-14B-ascend-int8` |
| Qwen3-14B-fp4 | ✓ | `models=Qwen3-14B-fp4` |
| Qwen3-14B-mixq-mix | ✓ | `models=Qwen3-14B-mixq-mix` |
| Qwen3-14B-mixq-w8a8 | ✓ | `models=Qwen3-14B-mixq-w8a8` |
| Qwen3-14B-w4-g128-symm-a8 | ✓ | `models=Qwen3-14B-w4-g128-symm-a8` |
| Qwen3-235B-A22B-Instruct-ascend-int8 | ✓ | `models=Qwen3-235B-A22B-Instruct-ascend-int8` |
| Qwen3-235B-A22B-ascend-int8 | ✓ | `models=Qwen3-235B-A22B-ascend-int8` |
| Qwen3-235B-A22B-mxfp4 | ✓ | `models=Qwen3-235B-A22B-mxfp4` |
| Qwen3-30B-A3B-mix-fp4-fp8 | ✓ | `models=Qwen3-30B-A3B-mix-fp4-fp8` |
| Qwen3-30B-A3B-mix-fp4-fp8 | ✓ | `models=Qwen3-30B-A3B-mix-fp4-fp8-merged` |
| Qwen3-30B-A3B-mxfp4 | ✓ | `models=Qwen3-30B-A3B-mxfp4` |
| Qwen3-32B-QServe-w4a8-g128 | ✓ | `models=Qwen3-32B-QServe-w4a8-g128` |
| Qwen3-32B-ascend-int8 | ✓ | `models=Qwen3-32B-ascend-int8` |
| Qwen3-32B-fp4 | ✓ | `models=Qwen3-32B-fp4-merged` |
| Qwen3-32B-mixq-mix | ✓ | `models=Qwen3-32B-mixq-mix` |
| Qwen3-32B-mxfp4 | ✓ | `models=Qwen3-32B-mxfp4` |
| Qwen3-32B-w4-g128-symm-a8 | ✓ | `models=Qwen3-32B-w4-g128-symm-a8` |
| Qwen3-4B-fp4 | ✓ | `models=Qwen3-4B-fp4` |
| Qwen3-4B-mxfp4 | ✓ | `models=Qwen3-4B-mxfp4` |
| Qwen3-8B-ascend-int8 | ✓ | `models=Qwen3-8B-ascend-int8` |
| Qwen3-Coder-480B-A35B-Instruct-int8 | ✓ | `models=Qwen3-Coder-480B-A35B-Instruct-int8` |

thu-pacman/chitu

简介

发行版

贡献者

语言

近期动态

thu-pacman/chitu .gitee-modal { width: 500px !important; }

简介

发行版

贡献者

语言

近期动态

搜索帮助

thu-pacman/chitu