Unsloth Dynamic 2.0 Quants New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. Image-Text-to-Text • 25B • Updated 6 days ago • 137k • 300 Text Generation • 754B • Updated 19 minutes ago • 74 Image-Text-to-Text • 1T • Updated 3 days ago • 24k • 131 Image-Text-to-Text • 426B • Updated 3 days ago • 20.5k • 98
Gemma 4 Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. Image-Text-to-Text • 12B • Updated 9 days ago • 579k • 646 Image-Text-to-Text • 25B • Updated 9 days ago • 1.16M • 883 Image-Text-to-Text • 31B • Updated 9 days ago • 540k • 492 Image-Text-to-Text • 8B • Updated 9 days ago • 739k • 508
Unsloth Diffusion GGUFs Find GGUFs and other variants of diffusion based models like Qwen-Image and FLUX. Image-to-Video • 21B • Updated Apr 20 • 260k • 465 Image-to-Image • 20B • Updated Jan 8 • 208k • 508 Text-to-Image • 20B • Updated Jan 6 • 54.8k • 383 Image-to-Video • 19B • Updated Jan 22 • 5.43k • 132
gpt-oss OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats. Text Generation • 21B • Updated Dec 19, 2025 • 227k • 718 Text Generation • 117B • Updated Aug 25, 2025 • 221k • 271 Text Generation • 21B • Updated Aug 8, 2025 • 81k • 38 Text Generation • 117B • Updated Aug 8, 2025 • 3.81k • 15
Qwen3-VL Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats. Image-Text-to-Text • 31B • Updated Jan 1 • 13.4k • 103 Image-Text-to-Text • 31B • Updated Jan 1 • 6.63k • 41 Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 22.6k • 51 Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 5.14k • 25
DeepSeek-V3.1 DeepSeek's new 3.1 update to their V3 models! 671B • Updated Sep 24, 2025 • 2.34k • 69 671B • Updated Sep 22, 2025 • 46.8k • 99 Text Generation • 685B • Updated Aug 21, 2025 • 29 • 3 Text Generation • 684B • Updated Aug 21, 2025 • 45 • 1
Embedding Models Run or fine-tune embedding models with Unsloth. Sentence Similarity • 0.3B • Updated Jan 22 • 82.1k • • 8 Sentence Similarity • 0.3B • Updated Sep 4, 2025 • 10.2k • 68 Feature Extraction • Updated Jan 22 • 2.97k • 8 Feature Extraction • 4B • Updated Jan 22 • 112k • 2
Ministral 3 Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes. 14B • Updated Dec 4, 2025 • 11.6k • 86 14B • Updated Dec 4, 2025 • 8.17k • 47 8B • Updated Dec 4, 2025 • 8.38k • 36 8B • Updated Dec 4, 2025 • 5.45k • 12
Gemma 3n Google Gemma 3n models, all versions including Dynamic GGUF, 4-bit, 16-bit and formats! Image-Text-to-Text • 7B • Updated Jun 30, 2025 • 9.68k • 205 Image-Text-to-Text • 4B • Updated Jul 17, 2025 • 14.1k • 60 Image-Text-to-Text • 8B • Updated Jul 11, 2025 • 2.35k • 9 Image-Text-to-Text • 8B • Updated Jul 11, 2025 • 273 • 4
Phi-4 (All Versions) 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 Text Generation • 15B • Updated May 1, 2025 • 6.47k • 92 Text Generation • 4B • Updated May 1, 2025 • 8.85k • 71 Text Generation • 15B • Updated May 1, 2025 • 2.66k • 23 Text Generation • 15B • Updated Jan 13, 2025 • 4.04k • 188
Deepseek V3 (All Versions) Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions. Text Generation • 671B • Updated Apr 28, 2025 • 2.55k • 23 Text Generation • 671B • Updated May 22, 2025 • 5.1k • 198 Text Generation • Updated Apr 21, 2025 • 34 • 8 Text Generation • 684B • Updated Jul 14, 2025 • 121 • 4
Mistral Small 3 (All Versions) A collection of Mistral's new Small 3.2 and 3 models including GGUF, 4-bit and more! Image-Text-to-Text • 24B • Updated Aug 26, 2025 • 28.7k • 175 Image-Text-to-Text • 24B • Updated Aug 26, 2025 • 2.92k • • 16 Image-Text-to-Text • Updated Jun 21, 2025 • 273 • 6 Image-Text-to-Text • 25B • Updated Jun 23, 2025 • 1.1k • 13
Llama 3.3 (All Versions) Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions. 71B • Updated May 10, 2025 • 37.3k • 119 Text Generation • 71B • Updated Nov 25, 2025 • 20.1k • • 51 Text Generation • 71B • Updated Nov 25, 2025 • 11k • 52
Qwen QwQ-32B Collection Qwen's reasoning models including QwQ (32B) & QVQ (72B) in formats: GGUF, dynamic 4-bit and 16-bit original versions. Text Generation • 33B • Updated Apr 27, 2025 • 3.51k • 86 Text Generation • 34B • Updated Mar 7, 2025 • 988 • 47 Text Generation • 33B • Updated Apr 27, 2025 • 83 • • 17 Text Generation • 34B • Updated Mar 5, 2025 • 182 • 4
Llama 3.2 Vision Meta's Llama 3.2 vision models 11B and 90B. Include 4-bit bnb and original versions. Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 7.34k • 88 Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 4.61k • 81 Image-Text-to-Text • 11B • Updated Nov 22, 2024 • 121 • 35 Image-Text-to-Text • 11B • Updated Nov 22, 2024 • 92 • 16
Llama 3.1 Collection Meta's Llama 3.1 models including 8B, 70B, 405B. Includes 4-bit bnb and original versions. Text Generation • 8B • Updated Feb 15, 2025 • 80.3k • 100 Text Generation • 8B • Updated Feb 15, 2025 • 14.6k • 4 Text Generation • 8B • Updated Feb 15, 2025 • 47.6k • 4 Text Generation • 8B • Updated Feb 15, 2025 • 15.1k • 110
Load 4bit models 4x faster Native bitsandbytes 4bit pre quantized models Text Generation • 3B • Updated Jun 2, 2025 • 9.88k • 22 Text Generation • 8B • Updated Feb 15, 2025 • 15.1k • 110 Text Generation • 8B • Updated Nov 22, 2024 • 55.7k • 134 Text Generation • 10B • Updated Jul 22, 2025 • 8.7k • 31
Gemma 4 QAT Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. Any-to-Any • 12B • Updated 8 days ago • 262k • 255 Image-Text-to-Text • 25B • Updated 8 days ago • 431k • 176 Image-Text-to-Text • 31B • Updated 8 days ago • 154k • 102 Any-to-Any • 7B • Updated 8 days ago • 101k • 75
Qwen3.6 Image-Text-to-Text • 27B • Updated Apr 22 • 792k • 798 Image-Text-to-Text • 35B • Updated Apr 20 • 1.02M • 1.24k Image-Text-to-Text • 10B • Updated Apr 22 • 16.8k • 57 Image-Text-to-Text • 12B • Updated Apr 22 • 13.1k • 38
Qwen3.5 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. Image-Text-to-Text • 27B • Updated Mar 5 • 119k • 493 Image-Text-to-Text • 35B • Updated Mar 5 • 127k • 841 Image-Text-to-Text • 9B • Updated Mar 2 • 772k • 692 Image-Text-to-Text • 4B • Updated Mar 2 • 628k • 279
Qwen3-Coder The Qwen3-Coder models deliver SOTA advancements in agentic coding and code tasks. Includes Qwen3-Coder-Next. Text Generation • 80B • Updated Mar 6 • 271k • 711 Text Generation • 80B • Updated Feb 3 • 5.72k • 43 Text Generation • 80B • Updated Mar 6 • 232 • 26 Text Generation • 80B • Updated Feb 3 • 9.8k • 9
Qwen3 Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. 31B • Updated Jul 31, 2025 • 663k • 310 4B • Updated Aug 20, 2025 • 66.6k • 181 4B • Updated Sep 11, 2025 • 4.82k • 100 235B • Updated Jul 25, 2025 • 2.14k • 84
DeepSeek R1 (All Versions) DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. Text Generation • 8B • Updated Jun 16, 2025 • 64.3k • 419 Text Generation • 671B • Updated Jun 15, 2025 • 5.34k • 199 Text Generation • 8B • Updated Jun 10, 2025 • 5.89k • 13 Text Generation • Updated Jun 10, 2025 • 72 • 15
Gemma 3 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. Text Generation • 0.3B • Updated Aug 15, 2025 • 118k • 164 Text Generation • 0.3B • Updated Aug 15, 2025 • 3.6k • 13 Text Generation • 0.3B • Updated Aug 14, 2025 • 15.4k • 23 Text Generation • 0.3B • Updated Aug 14, 2025 • 8.84k • 5
Granite 4.0 IBM's new Granite-4.0 models! Run Dynamic GGUFs or fine-tune with Unsloth. 0.4B • Updated Oct 28, 2025 • 4.26k • 8 0.3B • Updated Oct 28, 2025 • 1.42k • 9 1B • Updated Oct 28, 2025 • 2.37k • 19 2B • Updated Oct 28, 2025 • 1.62k • 7
Llama 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! Image-Text-to-Text • 108B • Updated Jun 17, 2025 • 28.1k • 157 Image-Text-to-Text • 401B • Updated Jun 18, 2025 • 10.1k • 49 Image-Text-to-Text • 109B • Updated Jun 17, 2025 • 1.21k • 55 Image-Text-to-Text • 112B • Updated Apr 12, 2025 • 390 • 80
Unsloth 4-bit Dynamic Quants Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit Text Generation • 8B • Updated Jul 18, 2025 • 16.6k • 37 Text Generation • 15B • Updated Feb 14, 2025 • 3.82k • 30 Text Generation • 8B • Updated Feb 14, 2025 • 23k • 25 Image-Text-to-Text • 12B • Updated May 12, 2025 • 6.64k • 24
Text-to-Speech (TTS) models 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! Text-to-Speech • 3B • Updated Jul 9, 2025 • 3.85k • 17 Text-to-Speech • 3B • Updated Mar 24, 2025 • 3.27k • 17 Text-to-Speech • 2B • Updated May 15, 2025 • 3.37k • 20 Automatic Speech Recognition • 2B • Updated May 14, 2025 • 3.89k • 16
Llama 3.2 Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. Text Generation • 1B • Updated May 9, 2025 • 23.3k • 66 Text Generation • 1B • Updated May 9, 2025 • 338k • 98 Text Generation • 1B • Updated Apr 26, 2025 • 51.5k • 4 Text Generation • 1B • Updated Jan 23, 2025 • 13.8k • 22
Qwen2.5-VL (All Versions) All versions of Qwen2.5-VL including the new 32B version and 4-bit, 16-bit and more! Image-Text-to-Text • 3B • Updated May 12, 2025 • 13k • 25 Image-Text-to-Text • 8B • Updated May 12, 2025 • 287k • 188 Image-Text-to-Text • 33B • Updated May 12, 2025 • 4.37k • 9 Image-Text-to-Text • 73B • Updated May 18, 2025 • 4.99k • 10
Vision/multimodal Models Collection of the most popular vision models including Llama 3.2, LlaVa, Qwen2 VL, Pixtral, PaliGemma and more! Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 7.34k • 88 Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 4.61k • 81 Image-Text-to-Text • 11B • Updated Dec 4, 2024 • 4.24k • 29 Image-Text-to-Text • 9B • Updated Nov 22, 2024 • 1.66k • 6
Qwen 2.5 Coder Complete collection of Code-specific model series for Qwen2.5 in bnb 4bit, 16bit and GGUF formats. 33B • Updated Nov 15, 2024 • 3.97k • 76 15B • Updated Nov 14, 2024 • 12.5k • 43 8B • Updated Nov 14, 2024 • 9.79k • 33 3B • Updated Nov 15, 2024 • 4.37k • 23
Qwen 2.5 Text Generation • 8B • Updated Apr 28, 2025 • 458k • 23 Text Generation • 8B • Updated Apr 28, 2025 • 88.9k • 27 Text Generation • 15B • Updated Apr 28, 2025 • 1.19k • 5 Text Generation • 8B • Updated Apr 28, 2025 • 30.3k • 7
4bit Instruct Models Text Generation • 3B • Updated Jun 2, 2025 • 69.4k • 36 Text Generation • 1B • Updated Jan 23, 2025 • 13.8k • 22 Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 4.61k • 81 Text Generation • 8B • Updated Feb 15, 2025 • 80.3k • 100
Unsloth Dynamic 2.0 Quants New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. Image-Text-to-Text • 25B • Updated 6 days ago • 137k • 300 Text Generation • 754B • Updated 19 minutes ago • 74 Image-Text-to-Text • 1T • Updated 3 days ago • 24k • 131 Image-Text-to-Text • 426B • Updated 3 days ago • 20.5k • 98
Gemma 4 QAT Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. Any-to-Any • 12B • Updated 8 days ago • 262k • 255 Image-Text-to-Text • 25B • Updated 8 days ago • 431k • 176 Image-Text-to-Text • 31B • Updated 8 days ago • 154k • 102 Any-to-Any • 7B • Updated 8 days ago • 101k • 75
Gemma 4 Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. Image-Text-to-Text • 12B • Updated 9 days ago • 579k • 646 Image-Text-to-Text • 25B • Updated 9 days ago • 1.16M • 883 Image-Text-to-Text • 31B • Updated 9 days ago • 540k • 492 Image-Text-to-Text • 8B • Updated 9 days ago • 739k • 508
Qwen3.6 Image-Text-to-Text • 27B • Updated Apr 22 • 792k • 798 Image-Text-to-Text • 35B • Updated Apr 20 • 1.02M • 1.24k Image-Text-to-Text • 10B • Updated Apr 22 • 16.8k • 57 Image-Text-to-Text • 12B • Updated Apr 22 • 13.1k • 38
Unsloth Diffusion GGUFs Find GGUFs and other variants of diffusion based models like Qwen-Image and FLUX. Image-to-Video • 21B • Updated Apr 20 • 260k • 465 Image-to-Image • 20B • Updated Jan 8 • 208k • 508 Text-to-Image • 20B • Updated Jan 6 • 54.8k • 383 Image-to-Video • 19B • Updated Jan 22 • 5.43k • 132
Qwen3.5 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. Image-Text-to-Text • 27B • Updated Mar 5 • 119k • 493 Image-Text-to-Text • 35B • Updated Mar 5 • 127k • 841 Image-Text-to-Text • 9B • Updated Mar 2 • 772k • 692 Image-Text-to-Text • 4B • Updated Mar 2 • 628k • 279
gpt-oss OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats. Text Generation • 21B • Updated Dec 19, 2025 • 227k • 718 Text Generation • 117B • Updated Aug 25, 2025 • 221k • 271 Text Generation • 21B • Updated Aug 8, 2025 • 81k • 38 Text Generation • 117B • Updated Aug 8, 2025 • 3.81k • 15
Qwen3-Coder The Qwen3-Coder models deliver SOTA advancements in agentic coding and code tasks. Includes Qwen3-Coder-Next. Text Generation • 80B • Updated Mar 6 • 271k • 711 Text Generation • 80B • Updated Feb 3 • 5.72k • 43 Text Generation • 80B • Updated Mar 6 • 232 • 26 Text Generation • 80B • Updated Feb 3 • 9.8k • 9
Qwen3-VL Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats. Image-Text-to-Text • 31B • Updated Jan 1 • 13.4k • 103 Image-Text-to-Text • 31B • Updated Jan 1 • 6.63k • 41 Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 22.6k • 51 Image-Text-to-Text • 4B • Updated Oct 31, 2025 • 5.14k • 25
Qwen3 Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. 31B • Updated Jul 31, 2025 • 663k • 310 4B • Updated Aug 20, 2025 • 66.6k • 181 4B • Updated Sep 11, 2025 • 4.82k • 100 235B • Updated Jul 25, 2025 • 2.14k • 84
DeepSeek-V3.1 DeepSeek's new 3.1 update to their V3 models! 671B • Updated Sep 24, 2025 • 2.34k • 69 671B • Updated Sep 22, 2025 • 46.8k • 99 Text Generation • 685B • Updated Aug 21, 2025 • 29 • 3 Text Generation • 684B • Updated Aug 21, 2025 • 45 • 1
DeepSeek R1 (All Versions) DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. Text Generation • 8B • Updated Jun 16, 2025 • 64.3k • 419 Text Generation • 671B • Updated Jun 15, 2025 • 5.34k • 199 Text Generation • 8B • Updated Jun 10, 2025 • 5.89k • 13 Text Generation • Updated Jun 10, 2025 • 72 • 15
Embedding Models Run or fine-tune embedding models with Unsloth. Sentence Similarity • 0.3B • Updated Jan 22 • 82.1k • • 8 Sentence Similarity • 0.3B • Updated Sep 4, 2025 • 10.2k • 68 Feature Extraction • Updated Jan 22 • 2.97k • 8 Feature Extraction • 4B • Updated Jan 22 • 112k • 2
Gemma 3 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. Text Generation • 0.3B • Updated Aug 15, 2025 • 118k • 164 Text Generation • 0.3B • Updated Aug 15, 2025 • 3.6k • 13 Text Generation • 0.3B • Updated Aug 14, 2025 • 15.4k • 23 Text Generation • 0.3B • Updated Aug 14, 2025 • 8.84k • 5
Ministral 3 Mistral Ministral 3: new multimodal models in Base, Instruct, and Reasoning variants, available in 3B, 8B, and 14B sizes. 14B • Updated Dec 4, 2025 • 11.6k • 86 14B • Updated Dec 4, 2025 • 8.17k • 47 8B • Updated Dec 4, 2025 • 8.38k • 36 8B • Updated Dec 4, 2025 • 5.45k • 12
Granite 4.0 IBM's new Granite-4.0 models! Run Dynamic GGUFs or fine-tune with Unsloth. 0.4B • Updated Oct 28, 2025 • 4.26k • 8 0.3B • Updated Oct 28, 2025 • 1.42k • 9 1B • Updated Oct 28, 2025 • 2.37k • 19 2B • Updated Oct 28, 2025 • 1.62k • 7
Gemma 3n Google Gemma 3n models, all versions including Dynamic GGUF, 4-bit, 16-bit and formats! Image-Text-to-Text • 7B • Updated Jun 30, 2025 • 9.68k • 205 Image-Text-to-Text • 4B • Updated Jul 17, 2025 • 14.1k • 60 Image-Text-to-Text • 8B • Updated Jul 11, 2025 • 2.35k • 9 Image-Text-to-Text • 8B • Updated Jul 11, 2025 • 273 • 4
Llama 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! Image-Text-to-Text • 108B • Updated Jun 17, 2025 • 28.1k • 157 Image-Text-to-Text • 401B • Updated Jun 18, 2025 • 10.1k • 49 Image-Text-to-Text • 109B • Updated Jun 17, 2025 • 1.21k • 55 Image-Text-to-Text • 112B • Updated Apr 12, 2025 • 390 • 80
Phi-4 (All Versions) 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 Text Generation • 15B • Updated May 1, 2025 • 6.47k • 92 Text Generation • 4B • Updated May 1, 2025 • 8.85k • 71 Text Generation • 15B • Updated May 1, 2025 • 2.66k • 23 Text Generation • 15B • Updated Jan 13, 2025 • 4.04k • 188
Unsloth 4-bit Dynamic Quants Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit Text Generation • 8B • Updated Jul 18, 2025 • 16.6k • 37 Text Generation • 15B • Updated Feb 14, 2025 • 3.82k • 30 Text Generation • 8B • Updated Feb 14, 2025 • 23k • 25 Image-Text-to-Text • 12B • Updated May 12, 2025 • 6.64k • 24
Deepseek V3 (All Versions) Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions. Text Generation • 671B • Updated Apr 28, 2025 • 2.55k • 23 Text Generation • 671B • Updated May 22, 2025 • 5.1k • 198 Text Generation • Updated Apr 21, 2025 • 34 • 8 Text Generation • 684B • Updated Jul 14, 2025 • 121 • 4
Text-to-Speech (TTS) models 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! Text-to-Speech • 3B • Updated Jul 9, 2025 • 3.85k • 17 Text-to-Speech • 3B • Updated Mar 24, 2025 • 3.27k • 17 Text-to-Speech • 2B • Updated May 15, 2025 • 3.37k • 20 Automatic Speech Recognition • 2B • Updated May 14, 2025 • 3.89k • 16
Mistral Small 3 (All Versions) A collection of Mistral's new Small 3.2 and 3 models including GGUF, 4-bit and more! Image-Text-to-Text • 24B • Updated Aug 26, 2025 • 28.7k • 175 Image-Text-to-Text • 24B • Updated Aug 26, 2025 • 2.92k • • 16 Image-Text-to-Text • Updated Jun 21, 2025 • 273 • 6 Image-Text-to-Text • 25B • Updated Jun 23, 2025 • 1.1k • 13
Llama 3.2 Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. Text Generation • 1B • Updated May 9, 2025 • 23.3k • 66 Text Generation • 1B • Updated May 9, 2025 • 338k • 98 Text Generation • 1B • Updated Apr 26, 2025 • 51.5k • 4 Text Generation • 1B • Updated Jan 23, 2025 • 13.8k • 22
Llama 3.3 (All Versions) Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions. 71B • Updated May 10, 2025 • 37.3k • 119 Text Generation • 71B • Updated Nov 25, 2025 • 20.1k • • 51 Text Generation • 71B • Updated Nov 25, 2025 • 11k • 52
Qwen2.5-VL (All Versions) All versions of Qwen2.5-VL including the new 32B version and 4-bit, 16-bit and more! Image-Text-to-Text • 3B • Updated May 12, 2025 • 13k • 25 Image-Text-to-Text • 8B • Updated May 12, 2025 • 287k • 188 Image-Text-to-Text • 33B • Updated May 12, 2025 • 4.37k • 9 Image-Text-to-Text • 73B • Updated May 18, 2025 • 4.99k • 10
Qwen QwQ-32B Collection Qwen's reasoning models including QwQ (32B) & QVQ (72B) in formats: GGUF, dynamic 4-bit and 16-bit original versions. Text Generation • 33B • Updated Apr 27, 2025 • 3.51k • 86 Text Generation • 34B • Updated Mar 7, 2025 • 988 • 47 Text Generation • 33B • Updated Apr 27, 2025 • 83 • • 17 Text Generation • 34B • Updated Mar 5, 2025 • 182 • 4
Vision/multimodal Models Collection of the most popular vision models including Llama 3.2, LlaVa, Qwen2 VL, Pixtral, PaliGemma and more! Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 7.34k • 88 Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 4.61k • 81 Image-Text-to-Text • 11B • Updated Dec 4, 2024 • 4.24k • 29 Image-Text-to-Text • 9B • Updated Nov 22, 2024 • 1.66k • 6
Llama 3.2 Vision Meta's Llama 3.2 vision models 11B and 90B. Include 4-bit bnb and original versions. Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 7.34k • 88 Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 4.61k • 81 Image-Text-to-Text • 11B • Updated Nov 22, 2024 • 121 • 35 Image-Text-to-Text • 11B • Updated Nov 22, 2024 • 92 • 16
Qwen 2.5 Coder Complete collection of Code-specific model series for Qwen2.5 in bnb 4bit, 16bit and GGUF formats. 33B • Updated Nov 15, 2024 • 3.97k • 76 15B • Updated Nov 14, 2024 • 12.5k • 43 8B • Updated Nov 14, 2024 • 9.79k • 33 3B • Updated Nov 15, 2024 • 4.37k • 23
Llama 3.1 Collection Meta's Llama 3.1 models including 8B, 70B, 405B. Includes 4-bit bnb and original versions. Text Generation • 8B • Updated Feb 15, 2025 • 80.3k • 100 Text Generation • 8B • Updated Feb 15, 2025 • 14.6k • 4 Text Generation • 8B • Updated Feb 15, 2025 • 47.6k • 4 Text Generation • 8B • Updated Feb 15, 2025 • 15.1k • 110
Qwen 2.5 Text Generation • 8B • Updated Apr 28, 2025 • 458k • 23 Text Generation • 8B • Updated Apr 28, 2025 • 88.9k • 27 Text Generation • 15B • Updated Apr 28, 2025 • 1.19k • 5 Text Generation • 8B • Updated Apr 28, 2025 • 30.3k • 7
Load 4bit models 4x faster Native bitsandbytes 4bit pre quantized models Text Generation • 3B • Updated Jun 2, 2025 • 9.88k • 22 Text Generation • 8B • Updated Feb 15, 2025 • 15.1k • 110 Text Generation • 8B • Updated Nov 22, 2024 • 55.7k • 134 Text Generation • 10B • Updated Jul 22, 2025 • 8.7k • 31
4bit Instruct Models Text Generation • 3B • Updated Jun 2, 2025 • 69.4k • 36 Text Generation • 1B • Updated Jan 23, 2025 • 13.8k • 22 Image-Text-to-Text • 11B • Updated Dec 10, 2024 • 4.61k • 81 Text Generation • 8B • Updated Feb 15, 2025 • 80.3k • 100