New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance.
AI & ML interests
Run and train models via Unsloth Desktop 🦥
Recent Activity
Qwen3.8 Unsloth quants including Qwen3.8-27B! Run and train Qwen3.8 with the Unsloth Desktop app.
Quants for Meta's new Muse Glimmer 30B model.
-
unsloth/Qwen3.6-27B-NVFP4
Image-Text-to-Text • 21B • Updated • 1.9M • 281 -
unsloth/Qwen3.6-35B-A3B-NVFP4
Image-Text-to-Text • 25B • Updated • 1.5M • 117 -
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast
Image-Text-to-Text • 22B • Updated • 151k • 118 -
unsloth/Qwen3.6-27B-GGUF
Image-Text-to-Text • 27B • Updated • 1.16M • 954
Find GGUFs and other variants of diffusion based models like Qwen-Image and FLUX.
OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats.
-
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 544k • 820 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 90k • 294 -
unsloth/gpt-oss-20b-unsloth-bnb-4bit
Text Generation • 21B • Updated • 62.9k • 39 -
unsloth/gpt-oss-120b-unsloth-bnb-4bit
Text Generation • 117B • Updated • 5.07k • 19
Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats.
-
unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF
Image-Text-to-Text • 31B • Updated • 24k • 115 -
unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF
Image-Text-to-Text • 31B • Updated • 9.06k • 43 -
unsloth/Qwen3-VL-4B-Instruct-GGUF
Image-Text-to-Text • 4B • Updated • 311k • 74 -
unsloth/Qwen3-VL-4B-Thinking-GGUF
Image-Text-to-Text • 4B • Updated • 6.54k • 25
DeepSeek's new 3.1 update to their V3 models!
Run or fine-tune embedding models with Unsloth.
-
unsloth/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 40.8k • • 11 -
unsloth/embeddinggemma-300m-GGUF
Sentence Similarity • 0.3B • Updated • 16.6k • 87 -
unsloth/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 6.18k • • 11 -
unsloth/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 55.2k • 4
Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes.
Google Gemma 3n models, all versions including Dynamic GGUF, 4-bit, 16-bit and formats!
-
unsloth/gemma-3n-E4B-it-GGUF
Image-Text-to-Text • 7B • Updated • 20.1k • 207 -
unsloth/gemma-3n-E2B-it-GGUF
Image-Text-to-Text • 4B • Updated • 21.1k • 61 -
unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit
Image-Text-to-Text • 8B • Updated • 894 • 9 -
unsloth/gemma-3n-E4B-unsloth-bnb-4bit
Image-Text-to-Text • 8B • Updated • 153 • 4
Microsoft's Phi-4 models including Reasoning + Reasoning Plus & mini. Includes Dynamic 2.0 GGUF, 4-bit & 16-bit versions. Includes Unsloth's bug fixes
Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions.
A collection of Mistral's new Small 3.2 and 3 models including GGUF, 4-bit and more!
-
unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF
Image-Text-to-Text • 24B • Updated • 44.3k • 193 -
unsloth/Mistral-Small-3.2-24B-Instruct-2506
Image-Text-to-Text • 24B • Updated • 3.89k • • 16 -
unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8
Image-Text-to-Text • Updated • 43 • 6 -
unsloth/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit
Image-Text-to-Text • 25B • Updated • 2.05k • 13
Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions.
Qwen's reasoning models including QwQ (32B) & QVQ (72B) in formats: GGUF, dynamic 4-bit and 16-bit original versions.
Meta's Llama 3.2 vision models 11B and 90B. Include 4-bit bnb and original versions.
-
unsloth/Llama-3.2-11B-Vision-Instruct
Image-Text-to-Text • 11B • Updated • 16k • 89 -
unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.99k • 87 -
unsloth/Llama-3.2-11B-Vision
Image-Text-to-Text • 11B • Updated • 443 • 34 -
unsloth/Llama-3.2-11B-Vision-bnb-4bit
Image-Text-to-Text • 11B • Updated • 91 • 17
Meta's Llama 3.1 models including 8B, 70B, 405B. Includes 4-bit bnb and original versions.
-
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Text Generation • 8B • Updated • 101k • 105 -
unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit
Text Generation • 8B • Updated • 16.5k • 4 -
unsloth/Meta-Llama-3.1-8B-Instruct-unsloth-bnb-4bit
Text Generation • 8B • Updated • 39.2k • 4 -
unsloth/Meta-Llama-3.1-8B-bnb-4bit
Text Generation • 8B • Updated • 13.5k • 112
Native bitsandbytes 4bit pre quantized models
-
unsloth/Llama-3.2-3B-bnb-4bit
Text Generation • 3B • Updated • 2.65k • 23 -
unsloth/Meta-Llama-3.1-8B-bnb-4bit
Text Generation • 8B • Updated • 13.5k • 112 -
unsloth/llama-3-8b-Instruct-bnb-4bit
Text Generation • 8B • Updated • 61.8k • 135 -
unsloth/gemma-2-9b-bnb-4bit
Text Generation • 10B • Updated • 9.16k • 31
Introducing Dynamic V3.0 quants, our new SOTA quantization methodology.
Dynamic Unsloth NVFP4 Quants. Faster and more accurate.
Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B.
-
unsloth/gemma-4-12b-it-GGUF
Image-Text-to-Text • 12B • Updated • 540k • 833 -
unsloth/gemma-4-26B-A4B-it-GGUF
Image-Text-to-Text • 25B • Updated • 647k • 1.12k -
unsloth/gemma-4-31B-it-GGUF
Image-Text-to-Text • 31B • Updated • 412k • 604 -
unsloth/gemma-4-E4B-it-GGUF
Image-Text-to-Text • 8B • Updated • 512k • 627
Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy.
-
unsloth/gemma-4-12B-it-qat-GGUF
Any-to-Any • 12B • Updated • 1.31M • 509 -
unsloth/gemma-4-26B-A4B-it-qat-GGUF
Image-Text-to-Text • 25B • Updated • 678k • 416 -
unsloth/gemma-4-31B-it-qat-GGUF
Image-Text-to-Text • 31B • Updated • 671k • 190 -
unsloth/gemma-4-E4B-it-qat-GGUF
Any-to-Any • 7B • Updated • 652k • 189
Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B.
The Qwen3-Coder models deliver SOTA advancements in agentic coding and code tasks. Includes Qwen3-Coder-Next.
Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants.
DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models.
-
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 52.2k • 448 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 4.25k • 202 -
unsloth/DeepSeek-R1-0528-Qwen3-8B-unsloth-bnb-4bit
Text Generation • 8B • Updated • 2.63k • 13 -
unsloth/DeepSeek-R1-0528
Text Generation • 685B • Updated • 110 • 15
All versions of Google's new multimodal models including QAT in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats.
-
unsloth/gemma-3-270m-it-GGUF
Text Generation • 0.3B • Updated • 71.7k • 174 -
unsloth/gemma-3-270m-it-qat-GGUF
Text Generation • 0.3B • Updated • 3.27k • 13 -
unsloth/gemma-3-270m-it
Text Generation • 0.3B • Updated • 33.3k • 24 -
unsloth/gemma-3-270m-it-unsloth-bnb-4bit
Text Generation • 0.3B • Updated • 10.9k • 6
IBM's new Granite-4.0 models! Run Dynamic GGUFs or fine-tune with Unsloth.
Meta's new Llama 4 multimodal models, Scout & Maverick. Includes Dynamic GGUFs, 16-bit & Dynamic 4-bit uploads. Run & fine-tune them with Unsloth!
-
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
Image-Text-to-Text • 108B • Updated • 39.7k • 164 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-Text-to-Text • 401B • Updated • 6.88k • 52 -
unsloth/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • 109B • Updated • 3.07k • 57 -
unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit
Image-Text-to-Text • 112B • Updated • 1.42k • 80
Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit
-
unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
Text Generation • 8B • Updated • 4.25k • 37 -
unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit
Text Generation • 15B • Updated • 3.62k • 30 -
unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit
Text Generation • 8B • Updated • 3.94k • 28 -
unsloth/gemma-3-12b-it-unsloth-bnb-4bit
Image-Text-to-Text • 12B • Updated • 7.36k • 24
A collection of 4-bit, Dynamic 4-bit and 16-bit voice models including Sesame-CSM, OpenAI's Whisper, Orpheus. Fine-tune them with Unsloth now!
Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions.
-
unsloth/Llama-3.2-1B-Instruct-GGUF
Text Generation • 1B • Updated • 40k • 71 -
unsloth/Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 403k • 101 -
unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit
Text Generation • 1B • Updated • 29k • 4 -
unsloth/Llama-3.2-1B-Instruct-bnb-4bit
Text Generation • 1B • Updated • 28k • 23
All versions of Qwen2.5-VL including the new 32B version and 4-bit, 16-bit and more!
-
unsloth/Qwen2.5-VL-3B-Instruct-GGUF
Image-Text-to-Text • 3B • Updated • 24.4k • 30 -
unsloth/Qwen2.5-VL-7B-Instruct-GGUF
Image-Text-to-Text • 8B • Updated • 161k • 226 -
unsloth/Qwen2.5-VL-32B-Instruct-GGUF
Image-Text-to-Text • 33B • Updated • 10.2k • 9 -
unsloth/Qwen2.5-VL-72B-Instruct-GGUF
Image-Text-to-Text • 73B • Updated • 3.82k • 11
Collection of the most popular vision models including Llama 3.2, LlaVa, Qwen2 VL, Pixtral, PaliGemma and more!
-
unsloth/Llama-3.2-11B-Vision-Instruct
Image-Text-to-Text • 11B • Updated • 16k • 89 -
unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.99k • 87 -
unsloth/Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.15k • 30 -
unsloth/Qwen2-VL-7B-Instruct-bnb-4bit
Image-Text-to-Text • 9B • Updated • 792 • 6
Complete collection of Code-specific model series for Qwen2.5 in bnb 4bit, 16bit and GGUF formats.
-
unsloth/Llama-3.2-3B-Instruct-bnb-4bit
Text Generation • 3B • Updated • 62.6k • 37 -
unsloth/Llama-3.2-1B-Instruct-bnb-4bit
Text Generation • 1B • Updated • 28k • 23 -
unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.99k • 87 -
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Text Generation • 8B • Updated • 101k • 105
New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance.
Introducing Dynamic V3.0 quants, our new SOTA quantization methodology.
Qwen3.8 Unsloth quants including Qwen3.8-27B! Run and train Qwen3.8 with the Unsloth Desktop app.
Dynamic Unsloth NVFP4 Quants. Faster and more accurate.
Quants for Meta's new Muse Glimmer 30B model.
Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B.
-
unsloth/gemma-4-12b-it-GGUF
Image-Text-to-Text • 12B • Updated • 540k • 833 -
unsloth/gemma-4-26B-A4B-it-GGUF
Image-Text-to-Text • 25B • Updated • 647k • 1.12k -
unsloth/gemma-4-31B-it-GGUF
Image-Text-to-Text • 31B • Updated • 412k • 604 -
unsloth/gemma-4-E4B-it-GGUF
Image-Text-to-Text • 8B • Updated • 512k • 627
-
unsloth/Qwen3.6-27B-NVFP4
Image-Text-to-Text • 21B • Updated • 1.9M • 281 -
unsloth/Qwen3.6-35B-A3B-NVFP4
Image-Text-to-Text • 25B • Updated • 1.5M • 117 -
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast
Image-Text-to-Text • 22B • Updated • 151k • 118 -
unsloth/Qwen3.6-27B-GGUF
Image-Text-to-Text • 27B • Updated • 1.16M • 954
Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy.
-
unsloth/gemma-4-12B-it-qat-GGUF
Any-to-Any • 12B • Updated • 1.31M • 509 -
unsloth/gemma-4-26B-A4B-it-qat-GGUF
Image-Text-to-Text • 25B • Updated • 678k • 416 -
unsloth/gemma-4-31B-it-qat-GGUF
Image-Text-to-Text • 31B • Updated • 671k • 190 -
unsloth/gemma-4-E4B-it-qat-GGUF
Any-to-Any • 7B • Updated • 652k • 189
Find GGUFs and other variants of diffusion based models like Qwen-Image and FLUX.
Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B.
OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats.
-
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 544k • 820 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 90k • 294 -
unsloth/gpt-oss-20b-unsloth-bnb-4bit
Text Generation • 21B • Updated • 62.9k • 39 -
unsloth/gpt-oss-120b-unsloth-bnb-4bit
Text Generation • 117B • Updated • 5.07k • 19
The Qwen3-Coder models deliver SOTA advancements in agentic coding and code tasks. Includes Qwen3-Coder-Next.
Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats.
-
unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF
Image-Text-to-Text • 31B • Updated • 24k • 115 -
unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF
Image-Text-to-Text • 31B • Updated • 9.06k • 43 -
unsloth/Qwen3-VL-4B-Instruct-GGUF
Image-Text-to-Text • 4B • Updated • 311k • 74 -
unsloth/Qwen3-VL-4B-Thinking-GGUF
Image-Text-to-Text • 4B • Updated • 6.54k • 25
Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants.
DeepSeek's new 3.1 update to their V3 models!
DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models.
-
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 52.2k • 448 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 4.25k • 202 -
unsloth/DeepSeek-R1-0528-Qwen3-8B-unsloth-bnb-4bit
Text Generation • 8B • Updated • 2.63k • 13 -
unsloth/DeepSeek-R1-0528
Text Generation • 685B • Updated • 110 • 15
Run or fine-tune embedding models with Unsloth.
-
unsloth/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 40.8k • • 11 -
unsloth/embeddinggemma-300m-GGUF
Sentence Similarity • 0.3B • Updated • 16.6k • 87 -
unsloth/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 6.18k • • 11 -
unsloth/Qwen3-Embedding-4B
Feature Extraction • 4B • Updated • 55.2k • 4
All versions of Google's new multimodal models including QAT in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats.
-
unsloth/gemma-3-270m-it-GGUF
Text Generation • 0.3B • Updated • 71.7k • 174 -
unsloth/gemma-3-270m-it-qat-GGUF
Text Generation • 0.3B • Updated • 3.27k • 13 -
unsloth/gemma-3-270m-it
Text Generation • 0.3B • Updated • 33.3k • 24 -
unsloth/gemma-3-270m-it-unsloth-bnb-4bit
Text Generation • 0.3B • Updated • 10.9k • 6
Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes.
IBM's new Granite-4.0 models! Run Dynamic GGUFs or fine-tune with Unsloth.
Google Gemma 3n models, all versions including Dynamic GGUF, 4-bit, 16-bit and formats!
-
unsloth/gemma-3n-E4B-it-GGUF
Image-Text-to-Text • 7B • Updated • 20.1k • 207 -
unsloth/gemma-3n-E2B-it-GGUF
Image-Text-to-Text • 4B • Updated • 21.1k • 61 -
unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit
Image-Text-to-Text • 8B • Updated • 894 • 9 -
unsloth/gemma-3n-E4B-unsloth-bnb-4bit
Image-Text-to-Text • 8B • Updated • 153 • 4
Meta's new Llama 4 multimodal models, Scout & Maverick. Includes Dynamic GGUFs, 16-bit & Dynamic 4-bit uploads. Run & fine-tune them with Unsloth!
-
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
Image-Text-to-Text • 108B • Updated • 39.7k • 164 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-Text-to-Text • 401B • Updated • 6.88k • 52 -
unsloth/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • 109B • Updated • 3.07k • 57 -
unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit
Image-Text-to-Text • 112B • Updated • 1.42k • 80
Microsoft's Phi-4 models including Reasoning + Reasoning Plus & mini. Includes Dynamic 2.0 GGUF, 4-bit & 16-bit versions. Includes Unsloth's bug fixes
Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit
-
unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
Text Generation • 8B • Updated • 4.25k • 37 -
unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit
Text Generation • 15B • Updated • 3.62k • 30 -
unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit
Text Generation • 8B • Updated • 3.94k • 28 -
unsloth/gemma-3-12b-it-unsloth-bnb-4bit
Image-Text-to-Text • 12B • Updated • 7.36k • 24
Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions.
A collection of 4-bit, Dynamic 4-bit and 16-bit voice models including Sesame-CSM, OpenAI's Whisper, Orpheus. Fine-tune them with Unsloth now!
A collection of Mistral's new Small 3.2 and 3 models including GGUF, 4-bit and more!
-
unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF
Image-Text-to-Text • 24B • Updated • 44.3k • 193 -
unsloth/Mistral-Small-3.2-24B-Instruct-2506
Image-Text-to-Text • 24B • Updated • 3.89k • • 16 -
unsloth/Mistral-Small-3.2-24B-Instruct-2506-FP8
Image-Text-to-Text • Updated • 43 • 6 -
unsloth/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit
Image-Text-to-Text • 25B • Updated • 2.05k • 13
Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions.
-
unsloth/Llama-3.2-1B-Instruct-GGUF
Text Generation • 1B • Updated • 40k • 71 -
unsloth/Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 403k • 101 -
unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit
Text Generation • 1B • Updated • 29k • 4 -
unsloth/Llama-3.2-1B-Instruct-bnb-4bit
Text Generation • 1B • Updated • 28k • 23
Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions.
All versions of Qwen2.5-VL including the new 32B version and 4-bit, 16-bit and more!
-
unsloth/Qwen2.5-VL-3B-Instruct-GGUF
Image-Text-to-Text • 3B • Updated • 24.4k • 30 -
unsloth/Qwen2.5-VL-7B-Instruct-GGUF
Image-Text-to-Text • 8B • Updated • 161k • 226 -
unsloth/Qwen2.5-VL-32B-Instruct-GGUF
Image-Text-to-Text • 33B • Updated • 10.2k • 9 -
unsloth/Qwen2.5-VL-72B-Instruct-GGUF
Image-Text-to-Text • 73B • Updated • 3.82k • 11
Qwen's reasoning models including QwQ (32B) & QVQ (72B) in formats: GGUF, dynamic 4-bit and 16-bit original versions.
Collection of the most popular vision models including Llama 3.2, LlaVa, Qwen2 VL, Pixtral, PaliGemma and more!
-
unsloth/Llama-3.2-11B-Vision-Instruct
Image-Text-to-Text • 11B • Updated • 16k • 89 -
unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.99k • 87 -
unsloth/Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.15k • 30 -
unsloth/Qwen2-VL-7B-Instruct-bnb-4bit
Image-Text-to-Text • 9B • Updated • 792 • 6
Meta's Llama 3.2 vision models 11B and 90B. Include 4-bit bnb and original versions.
-
unsloth/Llama-3.2-11B-Vision-Instruct
Image-Text-to-Text • 11B • Updated • 16k • 89 -
unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.99k • 87 -
unsloth/Llama-3.2-11B-Vision
Image-Text-to-Text • 11B • Updated • 443 • 34 -
unsloth/Llama-3.2-11B-Vision-bnb-4bit
Image-Text-to-Text • 11B • Updated • 91 • 17
Complete collection of Code-specific model series for Qwen2.5 in bnb 4bit, 16bit and GGUF formats.
Meta's Llama 3.1 models including 8B, 70B, 405B. Includes 4-bit bnb and original versions.
-
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Text Generation • 8B • Updated • 101k • 105 -
unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit
Text Generation • 8B • Updated • 16.5k • 4 -
unsloth/Meta-Llama-3.1-8B-Instruct-unsloth-bnb-4bit
Text Generation • 8B • Updated • 39.2k • 4 -
unsloth/Meta-Llama-3.1-8B-bnb-4bit
Text Generation • 8B • Updated • 13.5k • 112
Native bitsandbytes 4bit pre quantized models
-
unsloth/Llama-3.2-3B-bnb-4bit
Text Generation • 3B • Updated • 2.65k • 23 -
unsloth/Meta-Llama-3.1-8B-bnb-4bit
Text Generation • 8B • Updated • 13.5k • 112 -
unsloth/llama-3-8b-Instruct-bnb-4bit
Text Generation • 8B • Updated • 61.8k • 135 -
unsloth/gemma-2-9b-bnb-4bit
Text Generation • 10B • Updated • 9.16k • 31
-
unsloth/Llama-3.2-3B-Instruct-bnb-4bit
Text Generation • 3B • Updated • 62.6k • 37 -
unsloth/Llama-3.2-1B-Instruct-bnb-4bit
Text Generation • 1B • Updated • 28k • 23 -
unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit
Image-Text-to-Text • 11B • Updated • 5.99k • 87 -
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Text Generation • 8B • Updated • 101k • 105