[circle-check\\
Introducing Unsloth Studio: a new web UI for local AI\\
\\
🦥chevron-right](/content/docs/new/studio/index.html) close

Unsloth LLM 目录，适用于我们所有的 [动态arrow-up-right](https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs) Hugging Face 上的 GGUF、4 位、16 位模型。

• GGUF + 4 位

• 指令 16 位

• 基础 4 位和 16 位

• FP8

[Qwen](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog#qwen-models/index.html) [DeepSeek](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog#deepseek-models/index.html) [Gemma](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog#gemma-models/index.html) [Llama](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog#llama-models/index.html) [Mistral](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog#mistral-models/index.html) [GLM](/content/docs/get-started/unsloth-model-catalog#glm-models/index.html)

**GGUF** 可让你在以下工具中运行模型： [**Unsloth Studio**](/content/docs/zh/xin-zeng/studio/index.html) ✨、Ollama 和 llama.cpp。
**指令（4 位）** safetensors 可通过 Unsloth 用于推理或微调。

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#xin-zeng-qie-tui-jian-de-mo-xing/index.html)    **新增且推荐的模型：**

模型

变体

GGUF

指令（4 位）

[**Qwen3.6**](/content/docs/zh/mo-xing/qwen3.6)

35B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF)

—

[**Gemma 4**](/content/docs/zh/mo-xing/gemma-4/index.html)

26B-A4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF)

—

31B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-unsloth-bnb-4bit)

E4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-unsloth-bnb-4bit)

E2B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-unsloth-bnb-4bit)

[**Qwen3.5** arrow-up-right](https://github.com/unslothai/docs/blob/main/models/qwen3.5)

35B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF)

—

27B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-27B-GGUF)

—

122B-A10B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-122B-A10B-GGUF)

—

0.8B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF)

—

2B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-2B-GGUF)

—

4B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-4B-GGUF)

—

9B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-9B-GGUF)

—

397B-A17B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF)

—

**Qwen3**

[Coder-Next](/content/docs/zh/mo-xing/qwen3-coder-next/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF)

—

NVIDIA Nemotron 3

[Super-120B-A12B](/content/docs/zh/mo-xing/nemotron-3/nemotron-3-super/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4)

[Nano-4B](/content/docs/zh/mo-xing/nemotron-3/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF)

—

**GLM**

[4.7-Flash](/content/docs/zh/mo-xing/glm-4.7-flash/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF)

—

[5](/content/docs/zh/mo-xing/tutorials/glm-5/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-5-GGUF)

—

**Kimi**

[K2.5](/content/docs/zh/mo-xing/kimi-k2.5)

[链接arrow-up-right](https://huggingface.co/unsloth/Kimi-K2.5-GGUF)

—

[**gpt-oss**](/content/docs/zh/mo-xing/gpt-oss-how-to-run-and-fine-tune/index.html)

120B

[链接arrow-up-right](https://huggingface.co/unsloth/gpt-oss-120b-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gpt-oss-120b-unsloth-bnb-4bit)

20B

[链接arrow-up-right](https://huggingface.co/unsloth/gpt-oss-20b-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gpt-oss-20b-unsloth-bnb-4bit)

**MiniMax**

[M2.5](/content/docs/zh/mo-xing/tutorials/minimax-m25/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/MiniMax-M2.5-GGUF)

—

NVIDIA [Nemotron 3](/content/docs/zh/mo-xing/nemotron-3/index.html)

30B

[链接arrow-up-right](https://huggingface.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF)

—

[**Qwen-Image**](/content/docs/zh/mo-xing/tutorials/qwen-image-2512/index.html)

2512

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen-Image-2512-GGUF)

—

Edit-2511

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen-Image-Edit-2511-GGUF)

—

[**Ministral 3**](/content/docs/zh/mo-xing/tutorials/ministral-3/index.html)

3B

[指令arrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF) • [推理arrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Reasoning-2512-GGUF)

[指令arrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-unsloth-bnb-4bit) • [推理arrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Reasoning-2512-GGUF)

8B

[指令arrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Instruct-2512-GGUF) • [推理arrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Reasoning-2512-GGUF)

[指令arrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Instruct-2512-unsloth-bnb-4bit) • [推理arrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Reasoning-2512-unsloth-bnb-4bit)

14B

[指令arrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-GGUF) • [推理arrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Reasoning-2512-GGUF)

[指令arrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-unsloth-bnb-4bit) • [推理arrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Reasoning-2512-unsloth-bnb-4bit)

[**Devstral 2**](/content/docs/zh/mo-xing/tutorials/devstral-2/index.html)

24B

[链接arrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF)

—

123B

[链接arrow-up-right](https://huggingface.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF)

—

**Mistral Large 3**

675B

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Large-3-675B-Instruct-2512-NVFP4)

[**Qwen3-Next**](/content/docs/zh/mo-xing/tutorials/qwen3-next/index.html)

80B-A3B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Instruct-bnb-4bit/)

80B-A3B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF)

—

[**Qwen3-VL**](/content/docs/zh/mo-xing/tutorials/qwen3-how-to-run-and-fine-tune/qwen3-vl-how-to-run-and-fine-tune/index.html)

2B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit)

2B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit)

4B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit)

4B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit)

8B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit)

8B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit)

30B-A3B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF)

—

30B-A3B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF)

—

32B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Instruct-unsloth-bnb-4bit)

32B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Thinking-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Thinking-unsloth-bnb-4bit)

235B-A22B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF)

—

235B-A22B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF)

—

[**Qwen3-2507**](/content/docs/zh/mo-xing/tutorials/qwen3-next/index.html)

30B-A3B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF)

—

30B-A3B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF)

—

235B-A22B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF/)

—

[**Qwen3-Coder**](/content/docs/zh/mo-xing/tutorials/qwen3-coder-how-to-run-locally/index.html)

30B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF)

—

[**GLM**](/content/docs/zh/mo-xing/tutorials/glm-4.6-how-to-run-locally/index.html)

4.7

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.7-GGUF)

—

4.6V-Flash

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.6V-Flash-GGUF)

—

[**DeepSeek-V3.1**](/content/docs/zh/mo-xing/tutorials/deepseek-v3.1-how-to-run-locally/index.html)

Terminus

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-Terminus-GGUF)

—

V3.1

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF)

—

**Granite-4.0**

H-Small

[链接arrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-small-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-small-unsloth-bnb-4bit)

**Kimi-K2**

思考

[链接arrow-up-right](https://huggingface.co/unsloth/Kimi-K2-Thinking-GGUF)

—

0905

[链接arrow-up-right](https://huggingface.co/unsloth/Kimi-K2-Instruct-0905-GGUF)

—

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#deepseek-mo-xing/index.html)    **DeepSeek 模型：**

模型

变体

GGUF

指令（4 位）

**DeepSeek-V3.1**

Terminus

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-Terminus-GGUF)

V3.1

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF)

**DeepSeek-V3**

V3-0324

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF)

—

V3

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3-GGUF)

—

**DeepSeek-R1**

R1-0528

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF)

—

R1-0528-Qwen3-8B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-unsloth-bnb-4bit)

R1

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-GGUF)

—

R1 Zero

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Zero-GGUF)

—

蒸馏 Llama 3 8 B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit)

蒸馏 Llama 3.3 70 B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B-bnb-4bit)

蒸馏 Qwen 2.5 1.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit)

蒸馏 Qwen 2.5 7 B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit)

蒸馏 Qwen 2.5 14 B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit)

蒸馏 Qwen 2.5 32 B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit)

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#llama-mo-xing/index.html)    **Llama 模型：**

模型

变体

GGUF

指令（4 位）

**Llama 4**

Scout 17 B-16 E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit)

Maverick 17 B-128 E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF)

—

**Llama 3.3**

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-bnb-4bit)

**Llama 3.2**

1 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-bnb-4bit)

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit)

11 B 视觉

—

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bit)

90 B 视觉

—

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit)

**Llama 3.1**

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit)

70 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit)

405 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit)

**Llama 3**

8 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit)

70 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-70b-bnb-4bit)

**Llama 2**

7 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-7b-chat-bnb-4bit)

13 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit)

**CodeLlama**

7 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/codellama-7b-bnb-4bit)

13 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/codellama-13b-bnb-4bit)

34 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/codellama-34b-bnb-4bit)

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#gemma-mo-xing/index.html)    **Gemma 模型：**

模型

变体

GGUF

指令（4 位）

**Gemma 4**

E2B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-unsloth-bnb-4bit)

E4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-unsloth-bnb-4bit)

26B-A4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF)

—

31B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-unsloth-bnb-4bit)

**FunctionGemma**

270M

[链接arrow-up-right](https://huggingface.co/unsloth/functiongemma-270m-it-GGUF)

—

**Gemma 3n**

E2B

​ [链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it-unsloth-bnb-4bit)

E4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit)

**Gemma 3**

270M

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-270m-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-270m-it)

1 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it-unsloth-bnb-4bit)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it-unsloth-bnb-4bit)

12 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-it-unsloth-bnb-4bit)

27 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-it-unsloth-bnb-4bit)

**MedGemma**

4 B（视觉）

[链接arrow-up-right](https://huggingface.co/unsloth/medgemma-4b-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit)

27 B（视觉）

[链接arrow-up-right](https://huggingface.co/unsloth/medgemma-27b-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/medgemma-27b-text-it-unsloth-bnb-4bit)

**Gemma 2**

2 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2-it-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2-2b-it-bnb-4bit)

9 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2-9b-it-bnb-4bit)

27 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2-27b-it-bnb-4bit)

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#qwen-mo-xing/index.html)    **Qwen 模型：**

模型

变体

GGUF

指令（4 位）

[**Qwen3.5** arrow-up-right](https://github.com/unslothai/docs/blob/main/models/qwen3.5)

35B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF)

—

27B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-27B-GGUF)

—

122B-A10B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-122B-A10B-GGUF)

—

0.8B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF)

—

2B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-2B-GGUF)

—

4B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-4B-GGUF)

—

9B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-9B-GGUF)

—

397B-A17B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF)

—

**Qwen3**

[Coder-Next](/content/docs/zh/mo-xing/qwen3-coder-next/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF)

—

[**Qwen-Image**](/content/docs/zh/mo-xing/tutorials/qwen-image-2512/index.html)

2512

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen-Image-2512-GGUF)

—

Edit-2511

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen-Image-Edit-2511-GGUF)

—

[**Qwen3-VL**](/content/docs/zh/mo-xing/tutorials/qwen3-how-to-run-and-fine-tune/qwen3-vl-how-to-run-and-fine-tune/index.html)

2B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit)

2B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit)

4B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit)

4B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit)

8B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit)

8B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit)

**Qwen3-Coder**

30B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF)

—

480B-A35B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF)

—

[**Qwen3-2507**](/content/docs/zh/mo-xing/tutorials/qwen3-next/index.html)

30B-A3B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF)

—

30B-A3B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF)

—

235B-A22B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF/)

—

235B-A22B-指令

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF/)

—

**Qwen 3**

0.6 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-unsloth-bnb-4bit)

1.7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-unsloth-bnb-4bit)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-unsloth-bnb-4bit)

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-unsloth-bnb-4bit)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-unsloth-bnb-4bit)

30 B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-bnb-4bit)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-32B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-32B-unsloth-bnb-4bit)

235 B-A22B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF)

—

**Qwen 2.5 Omni**

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-3B-GGUF)

—

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-7B-GGUF)

—

**Qwen 2.5 VL**

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct-unsloth-bnb-4bit)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit)

72 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct-unsloth-bnb-4bit)

**Qwen 2.5**

0.5 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit)

1.5 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit)

3 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B-Instruct-bnb-4bit)

7 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct-bnb-4bit)

14 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct-bnb-4bit)

32 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B-Instruct-bnb-4bit)

72 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B-Instruct-bnb-4bit)

**Qwen 2.5 Coder（128 K）**

0.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-128K-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-bnb-4bit)

1.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-128K-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit)

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-128K-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-128K-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-128K-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit)

**QwQ**

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/QwQ-32B-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/QwQ-32B-unsloth-bnb-4bit)

**QVQ（预览）**

72 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/QVQ-72B-Preview-bnb-4bit)

**Qwen 2（聊天）**

1.5 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct-bnb-4bit)

7 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-7B-Instruct-bnb-4bit)

72 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-72B-Instruct-bnb-4bit)

**Qwen 2 VL**

2 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit)

7 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit)

72 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct-bnb-4bit)

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#glm-mo-xing/index.html)    **GLM 模型：**

模型

变体

GGUF

指令（4 位）

**GLM**

[4.7-Flash](/content/docs/zh/mo-xing/glm-4.7-flash/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF)

—

[5](/content/docs/zh/mo-xing/tutorials/glm-5/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-5-GGUF)

—

4.6V-Flash

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.6V-Flash-GGUF)

—

4.6

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.6-GGUF)

—

4.5-Air

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.5-Air-GGUF)

—

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#mistral-mo-xing/index.html)    **Mistral 模型：**

模型

变体

GGUF

指令（4 位）

**Magistral**

Small（2506）

[链接arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2506-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2506-unsloth-bnb-4bit)

Small（2509）

[链接arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-unsloth-bnb-4bit)

Small（2507）

[链接arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2507-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2507-unsloth-bnb-4bit)

**Mistral Small**

3.2-24 B（2506）

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit)

3.1-24 B（2503）

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-unsloth-bnb-4bit)

3-24 B（2501）

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit)

2409-22 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409-bnb-4bit)

**Devstral**

Small-24 B（2507）

[链接arrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2507-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2507-unsloth-bnb-4bit)

Small-24 B（2505）

[链接arrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2505-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2505-unsloth-bnb-4bit)

**Pixtral**

12 B（2409）

—

[链接arrow-up-right](https://huggingface.co/unsloth/Pixtral-12B-2409-bnb-4bit)

**Mistral NeMo**

12 B（2407）

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit)

**Mistral Large**

2407

—

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Large-Instruct-2407-bnb-4bit)

**Mistral 7 B**

v0.3

—

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit)

v0.2

—

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit)

**Mixtral**

8 × 7 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/Mixtral-8x7B-Instruct-v0.1-unsloth-bnb-4bit)

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#phi-mo-xing/index.html)    **Phi 模型：**

模型

变体

GGUF

指令（4 位）

**Phi-4**

推理增强版

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus-unsloth-bnb-4bit)

推理

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/phi-4-reasoning-unsloth-bnb-4bit)

迷你推理

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-reasoning-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-reasoning-unsloth-bnb-4bit)

Phi-4（指令）

[链接arrow-up-right](https://huggingface.co/unsloth/phi-4-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit)

mini（指令）

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit)

**Phi-3.5**

mini

—

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-3.5-mini-instruct-bnb-4bit)

**Phi-3**

mini

—

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct-bnb-4bit)

medium

—

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct-bnb-4bit)

#### [hashtag](/content/docs/zh/kai-shi-shi-yong/unsloth-model-catalog\#qi-ta-glmorpheussmolllava-deng-mo-xing/index.html)    **其他（GLM、Orpheus、Smol、Llava 等）模型：**

模型

变体

GGUF

指令（4 位）

GLM

4.5-Air

[链接arrow-up-right](https://huggingface.co/unsloth/GLM-4.5-Air-GGUF)

—

4.5

[4.5arrow-up-right](https://huggingface.co/unsloth/GLM-4.5-GGUF)

—

4-32B-0414

[4-32B-0414arrow-up-right](https://huggingface.co/unsloth/GLM-4-32B-0414-GGUF)

—

**Grok 2**

270B

[链接arrow-up-right](https://huggingface.co/unsloth/grok-2-GGUF)

—

**Baidu-ERNIE**

4.5-21B-A3B-思考

[链接arrow-up-right](https://huggingface.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF)

—

Hunyuan

A13B

[链接arrow-up-right](https://huggingface.co/unsloth/Hunyuan-A13B-Instruct-GGUF)

—

Orpheus

0.1-ft（3B）

[链接](/content/docs/index.html)

[链接arrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit)

**LLava**

1.5（7 B）

—

[链接arrow-up-right](https://huggingface.co/unsloth/llava-1.5-7b-hf-bnb-4bit)

1.6 Mistral（7 B）

—

[链接arrow-up-right](https://huggingface.co/unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit)

**TinyLlama**

聊天

—

[链接arrow-up-right](https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit)

**SmolLM 2**

135 M

[链接arrow-up-right](https://huggingface.co/unsloth/SmolLM2-135M-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/SmolLM2-135M-Instruct-bnb-4bit)

360 M

[链接arrow-up-right](https://huggingface.co/unsloth/SmolLM2-360M-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/SmolLM2-360M-Instruct-bnb-4bit)

1.7 B

[链接arrow-up-right](https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-GGUF)

[链接arrow-up-right](https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-bnb-4bit)

**Zephyr-SFT**

7 B

—

[链接arrow-up-right](https://huggingface.co/unsloth/zephyr-sft-bnb-4bit)

**Yi**

6 B（v1.5）

—

[链接arrow-up-right](https://huggingface.co/unsloth/Yi-1.5-6B-bnb-4bit)

6 B（v1.0）

—

[链接arrow-up-right](https://huggingface.co/unsloth/yi-6b-bnb-4bit)

34 B（聊天）

—

[链接arrow-up-right](https://huggingface.co/unsloth/yi-34b-chat-bnb-4bit)

34 B（基础）

—

[链接arrow-up-right](https://huggingface.co/unsloth/yi-34b-bnb-4bit)

16 位和 8 位指令模型用于在以下场景进行推理或微调： [**Unsloth Studio**](/content/docs/zh/xin-zeng/studio/index.html):

**新模型：**

模型

变体

指令（16 位）

**gpt-oss** （新）

20b

[链接arrow-up-right](https://huggingface.co/unsloth/gpt-oss-20b)

120b

[链接arrow-up-right](https://huggingface.co/unsloth/gpt-oss-120b)

**Gemma 3n**

E2B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it)

E4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it)

**DeepSeek-R1-0528**

R1-0528-Qwen3-8B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B)

R1-0528

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528)

**Mistral**

Small 3.2 24B（2506）

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506)

Small 3.1 24B（2503）

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503)

Small 3.0 24B（2501）

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501)

Magistral Small（2506）

[链接arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2506)

**Qwen 3**

0.6 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B)

1.7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B)

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B)

30B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-32B)

235B-A22B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B)

**Llama 4**

Scout 17B-16E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct)

Maverick 17B-128E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct)

**Qwen 2.5 Omni**

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-3B)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-7B)

**Phi-4**

推理增强版

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus)

推理

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning)

**DeepSeek 模型**

模型

变体

指令（16 位）

**DeepSeek-V3**

V3-0324

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3-0324)

V3

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3)

**DeepSeek-R1**

R1-0528

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528)

R1-0528-Qwen3-8B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B)

R1

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1)

R1 Zero

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Zero)

蒸馏 Llama 3 8B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B)

蒸馏 Llama 3.3 70B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B)

蒸馏 Qwen 2.5 1.5B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B)

蒸馏 Qwen 2.5 7B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B)

蒸馏 Qwen 2.5 14B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B)

蒸馏 Qwen 2.5 32B

[链接arrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B)

**Llama 模型**

系列

变体

指令（16 位）

**Llama 4**

Scout 17B-16E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct)

Maverick 17B-128E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct)

**Llama 3.3**

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct)

**Llama 3.2**

1 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct)

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct)

11 B 视觉

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision-Instruct)

90 B 视觉

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct)

**Llama 3.1**

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct)

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B-Instruct)

405 B

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-405B-Instruct)

**Llama 3**

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-8b-Instruct)

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-70b-Instruct)

**Llama 2**

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-7b-chat)

**Gemma 模型：**

模型

变体

指令（16 位）

**Gemma 3n**

E2B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it)

E4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it)

**Gemma 3**

1 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it)

12 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-it)

27 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-it)

**Gemma 2**

2 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2b-it)

9 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-9b-it)

27 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-27b-it)

**Qwen 模型：**

系列

变体

指令（16 位）

**Qwen 3**

0.6 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B)

1.7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B)

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B)

30B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-32B)

235B-A22B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B)

**Qwen 2.5 Omni**

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-3B)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-7B)

**Qwen 2.5 VL**

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct)

72 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct)

**Qwen 2.5**

0.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct)

1.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct)

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B-Instruct)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B-Instruct)

72 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B-Instruct)

**Qwen 2.5 Coder 128 K**

0.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-128K)

1.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-128K)

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-128K)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-128K)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-128K)

**QwQ**

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/QwQ-32B)

**QVQ（预览）**

72 B

—

**Qwen 2（聊天）**

1.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-7B-Instruct)

72 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-72B-Instruct)

**Qwen 2 VL**

2 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-2B-Instruct)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-7B-Instruct)

72 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct)

**Mistral 模型：**

模型

变体

指令（16 位）

**Mistral**

Small 2409-22B

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409)

**Mistral**

Large 2407

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Large-Instruct-2407)

**Mistral**

7B v0.3

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3)

**Mistral**

7B v0.2

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2)

**Pixtral**

12B 2409

[链接arrow-up-right](https://huggingface.co/unsloth/Pixtral-12B-2409)

**Mixtral**

8×7B

[链接arrow-up-right](https://huggingface.co/unsloth/Mixtral-8x7B-Instruct-v0.1)

**Mistral NeMo**

12B 2407

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407)

**Devstral**

Small 2505

[链接arrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2505)

**Phi 模型：**

模型

变体

指令（16 位）

**Phi-4**

推理增强版

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus)

推理

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning)

Phi-4（核心）

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4)

迷你推理

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-reasoning)

Mini

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-4-mini)

**Phi-3.5**

Mini

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-3.5-mini-instruct)

**Phi-3**

Mini

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct)

Medium

[链接arrow-up-right](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct)

**文本转语音（TTS）模型：**

模型

指令（16 位）

Orpheus-3B（v0.1 ft）

[链接arrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-ft)

Orpheus-3B（v0.1 pt）

[链接arrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained)

Sesame-CSM 1B

[链接arrow-up-right](https://huggingface.co/unsloth/csm-1b)

Whisper Large V3（语音转文本）

[链接arrow-up-right](https://huggingface.co/unsloth/whisper-large-v3)

Llasa-TTS 1B

[链接arrow-up-right](https://huggingface.co/unsloth/Llasa-1B)

Spark-TTS 0.5B

[链接arrow-up-right](https://huggingface.co/unsloth/Spark-TTS-0.5B)

Oute-TTS 1B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-OuteTTS-1.0-1B)

基础模型通常用于微调：

**新模型：**

模型

变体

基础（16 位）

基础（4 位）

**Gemma 3n**

E2B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-unsloth-bnb-4bit)

E4B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-unsloth-bnb-4bit)

**Qwen 3**

0.6 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit)

1.7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base-unsloth-bnb-4bit)

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base-unsloth-bnb-4bit)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base-unsloth-bnb-4bit)

30B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base-bnb-4bit)

**Llama 4**

Scout 17B 16E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E)

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit)

Maverick 17B 128E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E)

—

**Llama 模型：**

模型

变体

基础（16位）

基础（4位）

**Llama 4**

Scout 17B 16E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E)

—

Maverick 17B 128E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E)

—

**Llama 3.3**

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B)

—

**Llama 3.2**

1 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B)

—

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B)

—

11 B 视觉

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision)

—

90 B 视觉

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision)

—

**Llama 3.1**

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B)

—

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B)

—

**Llama 3**

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-8b)

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit)

**Llama 2**

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-7b)

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit)

13 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-13b)

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit)

**Qwen 模型：**

模型

变体

基础（16位）

基础（4位）

**Qwen 3**

0.6 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit)

1.7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base-unsloth-bnb-4bit)

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base-unsloth-bnb-4bit)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base-unsloth-bnb-4bit)

30B-A3B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base-unsloth-bnb-4bit)

**Qwen 2.5**

0.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B-bnb-4bit)

1.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B-bnb-4bit)

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B-bnb-4bit)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B-bnb-4bit)

14 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B-bnb-4bit)

32 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B-bnb-4bit)

72 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B-bnb-4bit)

**Qwen 2**

1.5 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B-bnb-4bit)

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-7B)

[链接arrow-up-right](https://huggingface.co/unsloth/Qwen2-7B-bnb-4bit)

**Llama 模型：**

模型

变体

基础（16位）

基础（4位）

**Llama 4**

Scout 17B 16E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E)

—

Maverick 17B 128E

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E)

—

**Llama 3.3**

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B)

—

**Llama 3.2**

1 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B)

—

3 B

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B)

—

11 B 视觉

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision)

—

90 B 视觉

[链接arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision)

—

**Llama 3.1**

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B)

—

70 B

[链接arrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B)

—

**Llama 3**

8 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-8b)

[链接arrow-up-right](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit)

**Llama 2**

7 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-7b)

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit)

13 B

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-13b)

[链接arrow-up-right](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit)

**Gemma 模型**

模型

变体

基础（16位）

基础（4位）

**Gemma 3**

1 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-pt)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-pt-unsloth-bnb-4bit)

4 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-pt)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-pt-unsloth-bnb-4bit)

12 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-pt)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-pt-unsloth-bnb-4bit)

27 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-pt)

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-pt-unsloth-bnb-4bit)

**Gemma 2**

2 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2-2b)

—

9 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2-9b)

—

27 B

[链接arrow-up-right](https://huggingface.co/unsloth/gemma-2-27b)

—

**Mistral 模型：**

模型

变体

基础（16位）

基础（4位）

**Mistral**

Small 24B 2501

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Base-2501)

—

NeMo 12B 2407

[链接arrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407)

—

7B v0.3

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.3)

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit)

7B v0.2

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.2)

[链接arrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.2-bnb-4bit)

Pixtral 12B 2409

[链接arrow-up-right](https://huggingface.co/unsloth/Pixtral-12B-Base-2409)

—

**其他（TTS、TinyLlama）模型：**

模型

变体

基础（16位）

基础（4位）

**TinyLlama**

1.1 B（基础）

[链接arrow-up-right](https://huggingface.co/unsloth/tinyllama)

[链接arrow-up-right](https://huggingface.co/unsloth/tinyllama-bnb-4bit)

**Orpheus-3b**

0.1-预训练

[链接arrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained)

[链接arrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained-unsloth-bnb-4bit)

你可以使用我们提供的 FP8 上传版本进行训练或服务/部署。

与 FP8 Block 相比，FP8 Dynamic 训练速度略快、VRAM 占用更低，但精度会有轻微损失。

模型

变体

FP8（动态 / 分块）

Qwen3

Coder-Next

[动态arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8)

GLM

4.7-Flash

[动态arrow-up-right](https://huggingface.co/unsloth/GLM-4.7-Flash-FP8-Dynamic)

**Llama 3.3**

70B 指令

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-FP8-Block)

**Llama 3.2**

1B 基础

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-FP8-Block)

1B 指令

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-FP8-Block)

3B 基础

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-FP8-Block)

3B 指令

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-FP8-Block)

**Llama 3.1**

8B 基础

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-FP8-Block)

8B 指令

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-FP8-Block)

70B 基础

[动态arrow-up-right](https://huggingface.co/unsloth/Llama-3.1-70B-FP8-Dynamic) · [分块arrow-up-right](https://huggingface.co/unsloth/Llama-3.1-70B-FP8-Block)

**Qwen3**

0.6B

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-FP8)

1.7B

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-FP8)

4B

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-FP8)

8B

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-FP8)

14B

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-FP8)

32B

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-32B-FP8)

235B-A22B

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-FP8)

**Qwen3（2507）**

4B 指令

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-FP8)

4B 思考

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Thinking-2507-FP8)

30B-A3B 指令

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-FP8)

30B-A3B 思考

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-FP8)

235B-A22B 指令

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-FP8)

235B-A22B 思考

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Thinking-2507-FP8)

**Qwen3-VL**

4B 指令

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-FP8)

4B 思考

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-FP8)

8B 指令

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-FP8)

8B 思考

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-FP8)

**Qwen3-Coder**

480B-A35B 指令

[FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-FP8)

**Granite 4.0**

h-tiny

[FP8 动态arrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-tiny-FP8-Dynamic)

h-small

[FP8 动态arrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-small-FP8-Dynamic)

**Magistral Small**

2509

[FP8 动态arrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-FP8-Dynamic) · [FP8 torchaoarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-FP8-torchao)

**Mistral Small 3.2**

24B 指令-2506

[FP8arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8)

**Gemma 3**

270M-it torchao
270m — [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-270m-it-FP8-Dynamic)
1B — [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it-FP8-Dynamic)
4B — [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it-FP8-Dynamic)
12B — [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-12B-it-FP8-Dynamic)
27B — [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-it-FP8-Dynamic)

[FP8 torchaoarrow-up-right](https://huggingface.co/unsloth/gemma-3-270m-it-torchao-FP8)

[上一页Unsloth 笔记本chevron-left](/content/docs/zh/kai-shi-shi-yong/unsloth-notebooks/index.html) [下一页Installationchevron-right](/content/docs/zh/kai-shi-shi-yong/install/index.html)

最后更新于 13天前

这有帮助吗？

本站使用 cookie 来提供服务并分析流量。浏览本站，即表示您接受 [隐私政策](https://policies.gitbook.com/privacy/cookies)。

close

接受拒绝
