[circle-check\\ Introducing Unsloth Studio: a new web UI for local AI\\ \\ πŸ¦₯chevron-right](/content/docs/new/studio/index.html) close Unsloth LLMs directory for all our [Dynamicarrow-up-right](https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs) GGUF, 4-bit, 16-bit models on Hugging Face. β€’ GGUF + 4-bit β€’ Instruct 16-bit β€’ Base 4 & 16-bit β€’ FP8 [Qwen](/content/docs/get-started/unsloth-model-catalog#qwen-models/index.html) [DeepSeek](/content/docs/get-started/unsloth-model-catalog#deepseek-models/index.html) [Gemma](/content/docs/get-started/unsloth-model-catalog#gemma-models/index.html) [Llama](/content/docs/get-started/unsloth-model-catalog#llama-models/index.html) [Mistral](/content/docs/get-started/unsloth-model-catalog#mistral-models/index.html) [GLM](/content/docs/get-started/unsloth-model-catalog#glm-models/index.html) **GGUFs** let you run models in tools like [**Unsloth Studio**](/content/docs/new/studio/index.html) ✨, Ollama and llama.cpp. **Instruct (4-bit)** safetensors can be used for inference or fine-tuning via Unsloth. #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#new-and-recommended-models/index.html) **New & recommended models:** Model Variant GGUF Instruct (4-bit) [**Qwen3.6**](/content/docs/models/qwen3.6) 27B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.6-27B-GGUF) β€” 35B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF) β€” [**Gemma 4**](/content/docs/models/gemma-4/index.html) 26B-A4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF) β€” 31B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-unsloth-bnb-4bit) E4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-unsloth-bnb-4bit) E2B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-unsloth-bnb-4bit) **Kimi** [**K2.6**](/content/docs/models/kimi-k2.6) [linkarrow-up-right](https://huggingface.co/unsloth/Kimi-K2.6-GGUF) β€” [**NVIDIA Nemotron 3**](/content/docs/models/nemotron-3-nano-omni/index.html) Nano-Omni-30B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF) β€” [**Qwen3.5** arrow-up-right](https://github.com/unslothai/docs/blob/main/models/qwen3.5) 35B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF) β€” 27B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-27B-GGUF) β€” 122B-A10B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-122B-A10B-GGUF) β€” 0.8B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF) β€” 2B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-2B-GGUF) β€” 4B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-4B-GGUF) β€” 9B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-9B-GGUF) β€” 397B-A17B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF) β€” **Qwen3** [Coder-Next](/content/docs/models/qwen3-coder-next/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF) β€” NVIDIA Nemotron 3 [Super-120B-A12B](/content/docs/models/nemotron-3/nemotron-3-super/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4) [Nano-4B](/content/docs/models/nemotron-3/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF) β€” **GLM** [4.7-Flash](/content/docs/models/tutorials/glm-4.7-flash/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF) β€” [5](/content/docs/models/tutorials/glm-5/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/GLM-5-GGUF) β€” **Kimi** [K2.5](/content/docs/models/tutorials/kimi-k2.5) [linkarrow-up-right](https://huggingface.co/unsloth/Kimi-K2.5-GGUF) β€” [**gpt-oss**](/content/docs/models/gpt-oss-how-to-run-and-fine-tune/index.html) 120B [linkarrow-up-right](https://huggingface.co/unsloth/gpt-oss-120b-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gpt-oss-120b-unsloth-bnb-4bit) 20B [linkarrow-up-right](https://huggingface.co/unsloth/gpt-oss-20b-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gpt-oss-20b-unsloth-bnb-4bit) **MiniMax** [M2.5](/content/docs/models/tutorials/minimax-m25/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/MiniMax-M2.5-GGUF) β€” NVIDIA [Nemotron 3](/content/docs/models/nemotron-3/index.html) 30B [linkarrow-up-right](https://huggingface.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF) β€” [**Qwen-Image**](/content/docs/models/tutorials/qwen-image-2512/index.html) 2512 [linkarrow-up-right](https://huggingface.co/unsloth/Qwen-Image-2512-GGUF) β€” Edit-2511 [linkarrow-up-right](https://huggingface.co/unsloth/Qwen-Image-Edit-2511-GGUF) β€” [**Ministral 3**](/content/docs/models/tutorials/ministral-3/index.html) 3B [Instructarrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF) β€’ [Reasoningarrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Reasoning-2512-GGUF) [Instructarrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-unsloth-bnb-4bit) β€’ [Reasoningarrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Reasoning-2512-GGUF) 8B [Instructarrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Instruct-2512-GGUF) β€’ [Reasoningarrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Reasoning-2512-GGUF) [Instructarrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Instruct-2512-unsloth-bnb-4bit) β€’ [Reasoningarrow-up-right](https://huggingface.co/unsloth/Ministral-3-8B-Reasoning-2512-unsloth-bnb-4bit) 14B [Instructarrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-GGUF) β€’ [Reasoningarrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Reasoning-2512-GGUF) [Instructarrow-up-right](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-unsloth-bnb-4bit) β€’ [Reasoningarrow-up-right](https://huggingface.co/unsloth/Ministral-3-14B-Reasoning-2512-unsloth-bnb-4bit) [**Devstral 2**](/content/docs/models/tutorials/devstral-2/index.html) 24B [linkarrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF) β€” 123B [linkarrow-up-right](https://huggingface.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF) β€” **Mistral Large 3** 675B [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Large-3-675B-Instruct-2512-NVFP4) [**Qwen3-Next**](/content/docs/models/tutorials/qwen3-next/index.html) 80B-A3B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Instruct-bnb-4bit/) 80B-A3B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF) β€” [**Qwen3-VL**](/content/docs/models/tutorials/qwen3-how-to-run-and-fine-tune/qwen3-vl-how-to-run-and-fine-tune/index.html) 2B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit) 2B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit) 4B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit) 4B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit) 8B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit) 8B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit) 30B-A3B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF) β€” 30B-A3B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF) β€” 32B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Instruct-unsloth-bnb-4bit) 32B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Thinking-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-32B-Thinking-unsloth-bnb-4bit) 235B-A22B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF) β€” 235B-A22B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF) β€” [**Qwen3-2507**](/content/docs/models/tutorials/qwen3-next/index.html) 30B-A3B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF) β€” 30B-A3B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF) β€” 235B-A22B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF/) β€” [**Qwen3-Coder**](/content/docs/models/tutorials/qwen3-coder-how-to-run-locally/index.html) 30B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF) β€” [**GLM**](/content/docs/models/tutorials/glm-4.6-how-to-run-locally/index.html) 4.7 [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.7-GGUF) β€” 4.6V-Flash [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.6V-Flash-GGUF) β€” [**DeepSeek-V3.1**](/content/docs/models/tutorials/deepseek-v3.1-how-to-run-locally/index.html) Terminus [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-Terminus-GGUF) β€” V3.1 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF) β€” **Granite-4.0** H-Small [linkarrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-small-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-small-unsloth-bnb-4bit) **Kimi-K2** Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Kimi-K2-Thinking-GGUF) β€” 0905 [linkarrow-up-right](https://huggingface.co/unsloth/Kimi-K2-Instruct-0905-GGUF) β€” #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#deepseek-models/index.html) **DeepSeek models:** Model Variant GGUF Instruct (4-bit) **DeepSeek-V3.1** Terminus [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-Terminus-GGUF) V3.1 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3.1-GGUF) **DeepSeek-V3** V3-0324 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF) β€” V3 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3-GGUF) β€” **DeepSeek-R1** R1-0528 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF) β€” R1-0528-Qwen3-8B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-unsloth-bnb-4bit) R1 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-GGUF) β€” R1 Zero [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Zero-GGUF) β€” Distill Llama 3 8 B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit) Distill Llama 3.3 70 B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B-bnb-4bit) Distill Qwen 2.5 1.5 B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit) Distill Qwen 2.5 7 B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit) Distill Qwen 2.5 14 B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit) Distill Qwen 2.5 32 B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit) #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#llama-models/index.html) **Llama models:** Model Variant GGUF Instruct (4-bit) **Llama 4** Scout 17 B-16 E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit) Maverick 17 B-128 E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF) β€” **Llama 3.3** 70 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-bnb-4bit) **Llama 3.2** 1 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-bnb-4bit) 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit) 11 B Vision β€” [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bit) 90 B Vision β€” [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit) **Llama 3.1** 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit) 70 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit) 405 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit) **Llama 3** 8 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) 70 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-70b-bnb-4bit) **Llama 2** 7 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-7b-chat-bnb-4bit) 13 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit) **CodeLlama** 7 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/codellama-7b-bnb-4bit) 13 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/codellama-13b-bnb-4bit) 34 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/codellama-34b-bnb-4bit) #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#gemma-models/index.html) **Gemma models:** Model Variant GGUF Instruct (4-bit) **Gemma 4** E2B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E2B-it-unsloth-bnb-4bit) E4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-E4B-it-unsloth-bnb-4bit) 26B-A4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF) β€” 31B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-4-31B-it-unsloth-bnb-4bit) **FunctionGemma** 270M [linkarrow-up-right](https://huggingface.co/unsloth/functiongemma-270m-it-GGUF) β€” **Gemma 3n** E2B ​ [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it-unsloth-bnb-4bit) E4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit) **Gemma 3** 270M [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-270m-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-270m-it) 1 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it-unsloth-bnb-4bit) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it-unsloth-bnb-4bit) 12 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-it-unsloth-bnb-4bit) 27 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-it-unsloth-bnb-4bit) **MedGemma** 4 B (vision) [linkarrow-up-right](https://huggingface.co/unsloth/medgemma-4b-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/medgemma-4b-it-unsloth-bnb-4bit) 27 B (vision) [linkarrow-up-right](https://huggingface.co/unsloth/medgemma-27b-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/medgemma-27b-text-it-unsloth-bnb-4bit) **Gemma 2** 2 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2-it-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2-2b-it-bnb-4bit) 9 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2-9b-it-bnb-4bit) 27 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2-27b-it-bnb-4bit) #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#qwen-models/index.html) **Qwen models:** Model Variant GGUF Instruct (4-bit) [**Qwen3.6**](/content/docs/models/qwen3.6) 27B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.6-27B-GGUF) β€” 35B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF) β€” [**Qwen3.5** arrow-up-right](https://github.com/unslothai/docs/blob/main/models/qwen3.5) 35B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF) β€” 27B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-27B-GGUF) β€” 122B-A10B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-122B-A10B-GGUF) β€” 0.8B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF) β€” 2B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-2B-GGUF) β€” 4B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-4B-GGUF) β€” 9B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-9B-GGUF) β€” 397B-A17B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF) β€” **Qwen3** [Coder-Next](/content/docs/models/qwen3-coder-next/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF) β€” [**Qwen-Image**](/content/docs/models/tutorials/qwen-image-2512/index.html) 2512 [linkarrow-up-right](https://huggingface.co/unsloth/Qwen-Image-2512-GGUF) β€” Edit-2511 [linkarrow-up-right](https://huggingface.co/unsloth/Qwen-Image-Edit-2511-GGUF) β€” [**Qwen3-VL**](/content/docs/models/tutorials/qwen3-how-to-run-and-fine-tune/qwen3-vl-how-to-run-and-fine-tune/index.html) 2B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit) 2B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit) 4B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit) 4B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit) 8B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit) 8B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit) **Qwen3-Coder** 30B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF) β€” 480B-A35B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF) β€” [**Qwen3-2507**](/content/docs/models/tutorials/qwen3-next/index.html) 30B-A3B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF) β€” 30B-A3B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF) β€” 235B-A22B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF/) β€” 235B-A22B-Instruct [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF/) β€” **Qwen 3** 0.6 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-unsloth-bnb-4bit) 1.7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-unsloth-bnb-4bit) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-unsloth-bnb-4bit) 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-unsloth-bnb-4bit) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-unsloth-bnb-4bit) 30 B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-bnb-4bit) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-32B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-32B-unsloth-bnb-4bit) 235 B-A22B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF) β€” **Qwen 2.5 Omni** 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-3B-GGUF) β€” 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-7B-GGUF) β€” **Qwen 2.5 VL** 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct-unsloth-bnb-4bit) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit) 72 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct-unsloth-bnb-4bit) **Qwen 2.5** 0.5 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit) 1.5 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit) 3 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B-Instruct-bnb-4bit) 7 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct-bnb-4bit) 14 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct-bnb-4bit) 32 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B-Instruct-bnb-4bit) 72 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B-Instruct-bnb-4bit) **Qwen 2.5 Coder (128 K)** 0.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-128K-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-bnb-4bit) 1.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-128K-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit) 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-128K-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-128K-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-128K-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit) **QwQ** 32 B [linkarrow-up-right](https://huggingface.co/unsloth/QwQ-32B-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/QwQ-32B-unsloth-bnb-4bit) **QVQ (preview)** 72 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/QVQ-72B-Preview-bnb-4bit) **Qwen 2 (chat)** 1.5 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct-bnb-4bit) 7 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-7B-Instruct-bnb-4bit) 72 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-72B-Instruct-bnb-4bit) **Qwen 2 VL** 2 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit) 7 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit) 72 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct-bnb-4bit) #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#glm-models/index.html) **GLM models:** Model Variant GGUF Instruct (4-bit) **GLM** [4.7-Flash](/content/docs/models/tutorials/glm-4.7-flash/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF) β€” [5](/content/docs/models/tutorials/glm-5/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/GLM-5-GGUF) β€” 4.6V-Flash [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.6V-Flash-GGUF) β€” 4.6 [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.6-GGUF) β€” 4.5-Air [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.5-Air-GGUF) β€” #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#mistral-models/index.html) **Mistral models:** Model Variant GGUF Instruct (4-bit) **Magistral** Small (2506) [linkarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2506-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2506-unsloth-bnb-4bit) Small (2509) [linkarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-unsloth-bnb-4bit) Small (2507) [linkarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2507-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2507-unsloth-bnb-4bit) **Mistral Small** 3.2-24 B (2506) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit) 3.1-24 B (2503) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-unsloth-bnb-4bit) 3-24 B (2501) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit) 2409-22 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409-bnb-4bit) **Devstral** Small-24 B (2507) [linkarrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2507-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2507-unsloth-bnb-4bit) Small-24 B (2505) [linkarrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2505-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2505-unsloth-bnb-4bit) **Pixtral** 12 B (2409) β€” [linkarrow-up-right](https://huggingface.co/unsloth/Pixtral-12B-2409-bnb-4bit) **Mistral NeMo** 12 B (2407) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit) **Mistral Large** 2407 β€” [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Large-Instruct-2407-bnb-4bit) **Mistral 7 B** v0.3 β€” [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit) v0.2 β€” [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) **Mixtral** 8 Γ— 7 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/Mixtral-8x7B-Instruct-v0.1-unsloth-bnb-4bit) #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#phi-models/index.html) **Phi models:** Model Variant GGUF Instruct (4-bit) **Phi-4** Reasoning-plus [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus-unsloth-bnb-4bit) Reasoning [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/phi-4-reasoning-unsloth-bnb-4bit) Mini-Reasoning [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-reasoning-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-reasoning-unsloth-bnb-4bit) Phi-4 (instruct) [linkarrow-up-right](https://huggingface.co/unsloth/phi-4-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit) mini (instruct) [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit) **Phi-3.5** mini β€” [linkarrow-up-right](https://huggingface.co/unsloth/Phi-3.5-mini-instruct-bnb-4bit) **Phi-3** mini β€” [linkarrow-up-right](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct-bnb-4bit) medium β€” [linkarrow-up-right](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct-bnb-4bit) #### [hashtag](/content/docs/get-started/unsloth-model-catalog\#other-glm-orpheus-smol-llava-etc.-models/index.html) **Other (GLM, Orpheus, Smol, Llava etc.) models:** Model Variant GGUF Instruct (4-bit) GLM 4.5-Air [linkarrow-up-right](https://huggingface.co/unsloth/GLM-4.5-Air-GGUF) β€” 4.5 [4.5arrow-up-right](https://huggingface.co/unsloth/GLM-4.5-GGUF) β€” 4-32B-0414 [4-32B-0414arrow-up-right](https://huggingface.co/unsloth/GLM-4-32B-0414-GGUF) β€” **Grok 2** 270B [linkarrow-up-right](https://huggingface.co/unsloth/grok-2-GGUF) β€” **Baidu-ERNIE** 4.5-21B-A3B-Thinking [linkarrow-up-right](https://huggingface.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF) β€” Hunyuan A13B [linkarrow-up-right](https://huggingface.co/unsloth/Hunyuan-A13B-Instruct-GGUF) β€” Orpheus 0.1-ft (3B) [link](/content/docs/index.html) [linkarrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit) **LLava** 1.5 (7 B) β€” [linkarrow-up-right](https://huggingface.co/unsloth/llava-1.5-7b-hf-bnb-4bit) 1.6 Mistral (7 B) β€” [linkarrow-up-right](https://huggingface.co/unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit) **TinyLlama** Chat β€” [linkarrow-up-right](https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit) **SmolLM 2** 135 M [linkarrow-up-right](https://huggingface.co/unsloth/SmolLM2-135M-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/SmolLM2-135M-Instruct-bnb-4bit) 360 M [linkarrow-up-right](https://huggingface.co/unsloth/SmolLM2-360M-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/SmolLM2-360M-Instruct-bnb-4bit) 1.7 B [linkarrow-up-right](https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-GGUF) [linkarrow-up-right](https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-bnb-4bit) **Zephyr-SFT** 7 B β€” [linkarrow-up-right](https://huggingface.co/unsloth/zephyr-sft-bnb-4bit) **Yi** 6 B (v1.5) β€” [linkarrow-up-right](https://huggingface.co/unsloth/Yi-1.5-6B-bnb-4bit) 6 B (v1.0) β€” [linkarrow-up-right](https://huggingface.co/unsloth/yi-6b-bnb-4bit) 34 B (chat) β€” [linkarrow-up-right](https://huggingface.co/unsloth/yi-34b-chat-bnb-4bit) 34 B (base) β€” [linkarrow-up-right](https://huggingface.co/unsloth/yi-34b-bnb-4bit) 16-bit and 8-bit Instruct models are used for inference or fine-tuning in [**Unsloth Studio**](/content/docs/new/studio/index.html): **New models:** Model Variant Instruct (16-bit) **gpt-oss** (new) 20b [linkarrow-up-right](https://huggingface.co/unsloth/gpt-oss-20b) 120b [linkarrow-up-right](https://huggingface.co/unsloth/gpt-oss-120b) **Gemma 3n** E2B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it) E4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it) **DeepSeek-R1-0528** R1-0528-Qwen3-8B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B) R1-0528 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528) **Mistral** Small 3.2 24B (2506) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506) Small 3.1 24B (2503) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503) Small 3.0 24B (2501) [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501) Magistral Small (2506) [linkarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2506) **Qwen 3** 0.6 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B) 1.7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B) 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B) 30B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-32B) 235B-A22B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B) **Llama 4** Scout 17B-16E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct) Maverick 17B-128E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct) **Qwen 2.5 Omni** 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-3B) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-7B) **Phi-4** Reasoning-plus [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus) Reasoning [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning) **DeepSeek models** Model Variant Instruct (16-bit) **DeepSeek-V3** V3-0324 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3-0324) V3 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-V3) **DeepSeek-R1** R1-0528 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528) R1-0528-Qwen3-8B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-0528-Qwen3-8B) R1 [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1) R1 Zero [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Zero) Distill Llama 3 8B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B) Distill Llama 3.3 70B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B) Distill Qwen 2.5 1.5B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B) Distill Qwen 2.5 7B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B) Distill Qwen 2.5 14B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-14B) Distill Qwen 2.5 32B [linkarrow-up-right](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B) **Llama models** Family Variant Instruct (16-bit) **Llama 4** Scout 17B-16E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct) Maverick 17B-128E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct) **Llama 3.3** 70 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct) **Llama 3.2** 1 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct) 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct) 11 B Vision [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision-Instruct) 90 B Vision [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct) **Llama 3.1** 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) 70 B [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B-Instruct) 405 B [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-405B-Instruct) **Llama 3** 8 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-8b-Instruct) 70 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-70b-Instruct) **Llama 2** 7 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-7b-chat) **Gemma models:** Model Variant Instruct (16-bit) **Gemma 3n** E2B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-it) E4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-it) **Gemma 3** 1 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it) 12 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-it) 27 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-it) **Gemma 2** 2 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2b-it) 9 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-9b-it) 27 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-27b-it) **Qwen models:** Family Variant Instruct (16-bit) **Qwen 3** 0.6 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B) 1.7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B) 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B) 30B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-32B) 235B-A22B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B) **Qwen 2.5 Omni** 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-3B) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Omni-7B) **Qwen 2.5 VL** 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-32B-Instruct) 72 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-VL-72B-Instruct) **Qwen 2.5** 0.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct) 1.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct) 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B-Instruct) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B-Instruct) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B-Instruct) 72 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B-Instruct) **Qwen 2.5 Coder 128 K** 0.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-0.5B-Instruct-128K) 1.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-128K) 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-128K) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-14B-Instruct-128K) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct-128K) **QwQ** 32 B [linkarrow-up-right](https://huggingface.co/unsloth/QwQ-32B) **QVQ (preview)** 72 B β€” **Qwen 2 (Chat)** 1.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-7B-Instruct) 72 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-72B-Instruct) **Qwen 2 VL** 2 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-2B-Instruct) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-7B-Instruct) 72 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-VL-72B-Instruct) **Mistral models:** Model Variant Instruct (16-bit) **Mistral** Small 2409-22B [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) **Mistral** Large 2407 [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Large-Instruct-2407) **Mistral** 7B v0.3 [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3) **Mistral** 7B v0.2 [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2) **Pixtral** 12B 2409 [linkarrow-up-right](https://huggingface.co/unsloth/Pixtral-12B-2409) **Mixtral** 8Γ—7B [linkarrow-up-right](https://huggingface.co/unsloth/Mixtral-8x7B-Instruct-v0.1) **Mistral NeMo** 12B 2407 [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407) **Devstral** Small 2505 [linkarrow-up-right](https://huggingface.co/unsloth/Devstral-Small-2505) **Phi models:** Model Variant Instruct (16-bit) **Phi-4** Reasoning-plus [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning-plus) Reasoning [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-reasoning) Phi-4 (core) [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4) Mini-Reasoning [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-mini-reasoning) Mini [linkarrow-up-right](https://huggingface.co/unsloth/Phi-4-mini) **Phi-3.5** Mini [linkarrow-up-right](https://huggingface.co/unsloth/Phi-3.5-mini-instruct) **Phi-3** Mini [linkarrow-up-right](https://huggingface.co/unsloth/Phi-3-mini-4k-instruct) Medium [linkarrow-up-right](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct) **Text-to-Speech (TTS) models:** Model Instruct (16-bit) Orpheus-3B (v0.1 ft) [linkarrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-ft) Orpheus-3B (v0.1 pt) [linkarrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained) Sesame-CSM 1B [linkarrow-up-right](https://huggingface.co/unsloth/csm-1b) Whisper Large V3 (STT) [linkarrow-up-right](https://huggingface.co/unsloth/whisper-large-v3) Llasa-TTS 1B [linkarrow-up-right](https://huggingface.co/unsloth/Llasa-1B) Spark-TTS 0.5B [linkarrow-up-right](https://huggingface.co/unsloth/Spark-TTS-0.5B) Oute-TTS 1B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-OuteTTS-1.0-1B) Base models are usually used for fine-tuning purposes: **New models:** Model Variant Base (16-bit) Base (4-bit) **Gemma 3n** E2B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E2B-unsloth-bnb-4bit) E4B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3n-E4B-unsloth-bnb-4bit) **Qwen 3** 0.6 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit) 1.7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base-unsloth-bnb-4bit) 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base-unsloth-bnb-4bit) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base-unsloth-bnb-4bit) 30B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base-bnb-4bit) **Llama 4** Scout 17B 16E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E) [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit) Maverick 17B 128E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E) β€” **Llama models:** Model Variant BaseΒ (16-bit) BaseΒ (4-bit) **Llama 4** Scout 17B 16E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E) β€” Maverick 17B 128E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E) β€” **Llama 3.3** 70 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B) β€” **Llama 3.2** 1 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B) β€” 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B) β€” 11 B Vision [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision) β€” 90 B Vision [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision) β€” **Llama 3.1** 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) β€” 70 B [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B) β€” **Llama 3** 8 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-8b) [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) **Llama 2** 7 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-7b) [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) 13 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-13b) [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit) **Qwen models:** Model Variant BaseΒ (16-bit) BaseΒ (4-bit) **Qwen 3** 0.6 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit) 1.7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Base-unsloth-bnb-4bit) 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-8B-Base-unsloth-bnb-4bit) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-14B-Base-unsloth-bnb-4bit) 30B-A3B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Base-unsloth-bnb-4bit) **Qwen 2.5** 0.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-0.5B-bnb-4bit) 1.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-1.5B-bnb-4bit) 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-3B-bnb-4bit) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-7B-bnb-4bit) 14 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-14B-bnb-4bit) 32 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-32B-bnb-4bit) 72 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2.5-72B-bnb-4bit) **Qwen 2** 1.5 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-1.5B-bnb-4bit) 7 B [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-7B) [linkarrow-up-right](https://huggingface.co/unsloth/Qwen2-7B-bnb-4bit) **Llama models:** Model Variant BaseΒ (16-bit) BaseΒ (4-bit) **Llama 4** Scout 17B 16E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Scout-17B-16E) β€” Maverick 17B 128E [linkarrow-up-right](https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E) β€” **Llama 3.3** 70 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B) β€” **Llama 3.2** 1 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B) β€” 3 B [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B) β€” 11 B Vision [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-11B-Vision) β€” 90 B Vision [linkarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-90B-Vision) β€” **Llama 3.1** 8 B [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) β€” 70 B [linkarrow-up-right](https://huggingface.co/unsloth/Meta-Llama-3.1-70B) β€” **Llama 3** 8 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-8b) [linkarrow-up-right](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) **Llama 2** 7 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-7b) [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) 13 B [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-13b) [linkarrow-up-right](https://huggingface.co/unsloth/llama-2-13b-bnb-4bit) **Gemma models** Model Variant BaseΒ (16-bit) BaseΒ (4-bit) **Gemma 3** 1 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-pt) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-pt-unsloth-bnb-4bit) 4 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-pt) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-pt-unsloth-bnb-4bit) 12 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-pt) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-12b-pt-unsloth-bnb-4bit) 27 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-pt) [linkarrow-up-right](https://huggingface.co/unsloth/gemma-3-27b-pt-unsloth-bnb-4bit) **Gemma 2** 2 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2-2b) β€” 9 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2-9b) β€” 27 B [linkarrow-up-right](https://huggingface.co/unsloth/gemma-2-27b) β€” **Mistral models:** Model Variant BaseΒ (16-bit) BaseΒ (4-bit) **Mistral** Small 24B 2501 [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Small-24B-Base-2501) β€” NeMo 12B 2407 [linkarrow-up-right](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407) β€” 7B v0.3 [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.3) [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) 7B v0.2 [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.2) [linkarrow-up-right](https://huggingface.co/unsloth/mistral-7b-v0.2-bnb-4bit) Pixtral 12B 2409 [linkarrow-up-right](https://huggingface.co/unsloth/Pixtral-12B-Base-2409) β€” **Other (TTS, TinyLlama) models:** Model Variant BaseΒ (16-bit) BaseΒ (4-bit) **TinyLlama** 1.1 B (Base) [linkarrow-up-right](https://huggingface.co/unsloth/tinyllama) [linkarrow-up-right](https://huggingface.co/unsloth/tinyllama-bnb-4bit) **Orpheus-3b** 0.1-pretrained [linkarrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained) [linkarrow-up-right](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained-unsloth-bnb-4bit) You can use our FP8 uploads for training or serving/deployment. FP8 Dynamic offers slightly faster training and lower VRAM usage than FP8 Block, but with a small trade-off in accuracy. Model Variant FP8 (Dynamic / Block) Qwen3 Coder-Next [Dynamicarrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8) GLM 4.7-Flash [Dynamicarrow-up-right](https://huggingface.co/unsloth/GLM-4.7-Flash-FP8-Dynamic) **Llama 3.3** 70B Instruct [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct-FP8-Block) **Llama 3.2** 1B Base [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-FP8-Block) 1B Instruct [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct-FP8-Block) 3B Base [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-FP8-Block) 3B Instruct [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-FP8-Block) **Llama 3.1** 8B Base [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-FP8-Block) 8B Instruct [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-FP8-Dynamic) Β· [Blockarrow-up-right](https://huggingface.co/unsloth/Llama-3.1-8B-Instruct-FP8-Block) 70B Base [Dynamicarrow-up-right](https://huggingface.co/unsloth/Llama-3.1-70B-FP8-Dynamic) Β· [Blockarrow-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 Instruct [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-FP8) 4B Thinking [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-4B-Thinking-2507-FP8) 30B-A3B Instruct [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-FP8) 30B-A3B Thinking [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-30B-A3B-Thinking-2507-FP8) 235B-A22B Instruct [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507-FP8) 235B-A22B Thinking [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-235B-A22B-Thinking-2507-FP8) **Qwen3-VL** 4B Instruct [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Instruct-FP8) 4B Thinking [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-4B-Thinking-FP8) 8B Instruct [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-FP8) 8B Thinking [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-FP8) **Qwen3-Coder** 480B-A35B Instruct [FP8arrow-up-right](https://huggingface.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-FP8) **Granite 4.0** h-tiny [FP8 Dynamicarrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-tiny-FP8-Dynamic) h-small [FP8 Dynamicarrow-up-right](https://huggingface.co/unsloth/granite-4.0-h-small-FP8-Dynamic) **Magistral Small** 2509 [FP8 Dynamicarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-FP8-Dynamic) Β· [FP8 torchaoarrow-up-right](https://huggingface.co/unsloth/Magistral-Small-2509-FP8-torchao) **Mistral Small 3.2** 24B Instruct-2506 [FP8arrow-up-right](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8) **Gemma 3** 270M-it torchao 270m β€” [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-270m-it-FP8-Dynamic) 1B β€” [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-1b-it-FP8-Dynamic) 4B β€” [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-4b-it-FP8-Dynamic) 12B β€” [FP8arrow-up-right](https://huggingface.co/unsloth/gemma-3-12B-it-FP8-Dynamic) 27B β€” [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) [PreviousUnsloth Notebookschevron-left](/content/docs/get-started/unsloth-notebooks/index.html) [NextInstallationchevron-right](/content/docs/get-started/install/index.html) Last updated 11 hours ago Was this helpful? This site uses cookies to deliver its service and to analyze traffic. By browsing this site, you accept the [privacy policy](https://policies.gitbook.com/privacy/cookies). close AcceptReject