publisher

unsloth

74 builds measured across 62 families, and 36 derivatives of other people's models. Ranked by what machines proved, never by downloads.

measured — signed by the machine that ran eachhf.co/unsloth/gemma-4-12b-it-GGUF:Q8_0gemma-4/12b · Q8_0 · ollama · 2,62,144 ctx · 18.6 tok/s hf.co/unsloth/gemma-4-12b-it-GGUF:BF16gemma-4/12b · BF16 · ollama · 1,31,072 ctx · 10.7 tok/s hf.co/unsloth/gemma-4-12b-it-GGUF:IQ4_XSgemma-4/12b · IQ4_XS · ollama · 1,31,072 ctx · 23.2 tok/s hf.co/unsloth/gemma-4-12b-it-GGUF:Q4_K_Mgemma-4/12b · Q4_K_M · ollama · 1,31,072 ctx · 29.1 tok/s hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q8_0gemma-4/26b-a4b · Q8_0 · ollama · 1,31,072 ctx · 20.7 tok/s hf.co/unsloth/gemma-4-31B-it-GGUF:Q4_0gemma-4/31b · Q4_0 · ollama · 1,31,072 ctx · 2.4 tok/s hf.co/unsloth/gemma-4-31B-it-GGUF:Q4_K_Mgemma-4/31b · Q4_K_M · ollama · 1,31,072 ctx · 3.4 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:BF16gemma-4/e2b · BF16 · ollama · 1,31,072 ctx · 38.3 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ4_XSgemma-4/e2b · IQ4_XS · ollama · 1,31,072 ctx · 174.7 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_0gemma-4/e2b · Q4_0 · ollama · 1,31,072 ctx · 84.7 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_K_Mgemma-4/e2b · Q4_K_M · ollama · 1,31,072 ctx · 164.7 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:Q8_0gemma-4/e2b · Q8_0 · ollama · 1,31,072 ctx · 67.0 tok/s hf.co/unsloth/gemma-4-E4B-it-GGUF:BF16gemma-4/e4b · BF16 · ollama · 1,31,072 ctx · 25.8 tok/s hf.co/unsloth/gemma-4-E4B-it-GGUF:IQ4_XSgemma-4/e4b · IQ4_XS · ollama · 1,31,072 ctx · 61.4 tok/s hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_0gemma-4/e4b · Q4_0 · ollama · 1,31,072 ctx · 54.7 tok/s hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_Mgemma-4/e4b · Q4_K_M · ollama · 1,31,072 ctx · 56.8 tok/s hf.co/unsloth/gemma-4-E4B-it-GGUF:Q8_0gemma-4/e4b · Q8_0 · ollama · 1,31,072 ctx · 39.5 tok/s hf.co/unsloth/Phi-4-mini-instruct-GGUF:BF16phi-4/mini · BF16 · ollama · 1,31,072 ctx · 32.0 tok/s hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q3_K_Mphi-4/mini · Q3_K_M · ollama · 1,31,072 ctx · 66.9 tok/s hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q4_K_Mphi-4/mini · Q4_K_M · ollama · 1,31,072 ctx · 75.3 tok/s hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q5_K_Mphi-4/mini · Q5_K_M · ollama · 1,31,072 ctx · 68.7 tok/s hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q8_0phi-4/mini · Q8_0 · ollama · 1,31,072 ctx · 53.7 tok/s hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_Mqwen-3/30b-a3b · Q4_K_M · ollama · 1,31,072 ctx · 26.7 tok/s hf.co/unsloth/gemma-3-270m-it-GGUF:Q8_0gemma-3/270m · Q8_0 · ollama · 32,768 ctx · 31.3 tok/s hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q4_K_Mphi-4/reasoning-plus · Q4_K_M · ollama · 32,768 ctx · 24.5 tok/s hf.co/unsloth/Qwen3-4B-GGUF:IQ3_XXSqwen-3/4b · IQ3_XXS · ollama · 32,768 ctx · 62.9 tok/s hf.co/unsloth/gemma-3-270m-it-GGUF:F16gemma-3/270m · F16 · ollama · 16,384 ctx · 23.5 tok/s hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:F16llama-3-2/3b · F16 · ollama · 16,384 ctx · 94.9 tok/s hf.co/unsloth/Qwen3-4B-GGUF:BF16qwen-3/4b · BF16 · ollama · 16,384 ctx · 80.8 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ4_NLgemma-4/e2b · IQ4_NL · ollama · 8,192 ctx · 54.9 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:Q3_K_Mgemma-4/e2b · Q3_K_M · ollama · 8,192 ctx · 38.4 tok/s hf.co/unsloth/gemma-4-E2B-it-GGUF:Q3_K_Sgemma-4/e2b · Q3_K_S · ollama · 4,096 ctx · 14.4 tok/s hf.co/unsloth/gemma-4-E4B-it-GGUF:Q3_K_Mgemma-4/e4b · Q3_K_M · ollama · 4,096 ctx · 20.4 tok/s hf.co/unsloth/LFM2.5-1.2B-Instruct-GGUF:Q4_K_Mlfm-2-5/1.2b · Q4_K_M · ollama · 4,096 ctx · 16.1 tok/s hf.co/unsloth/Phi-4-mini-reasoning-GGUF:IQ3_XXSphi-4/mini-reasoning · IQ3_XXS · ollama · 4,096 ctx · 189.4 tok/s hf.co/unsloth/Qwen3-VL-4B-Instruct-GGUF:IQ4_XSqwen-3/4b · IQ4_XS · ollama · 4,096 ctx · 6.4 tok/s hf.co/unsloth/Qwen3-VL-4B-Instruct-GGUF:Q4_0qwen-3/4b · Q4_0 · ollama · 4,096 ctx · 40.9 tok/s hf.co/unsloth/Qwen3-VL-4B-Instruct-GGUF:Q4_1qwen-3/4b · Q4_1 · ollama · 4,096 ctx · 37.0 tok/s hf.co/unsloth/embeddinggemma-300m-GGUF:BF16embeddinggemma/300m · BF16 · ollama hf.co/unsloth/embeddinggemma-300m-GGUF:F32embeddinggemma/300m · F32 · ollama hf.co/unsloth/embeddinggemma-300m-GGUF:Q4_0embeddinggemma/300m · Q4_0 · ollama hf.co/unsloth/functiongemma-270m-it-GGUF:BF16functiongemma/270m · BF16 · ollama · 18.7 tok/s hf.co/unsloth/functiongemma-270m-it-GGUF:IQ2_Mfunctiongemma/270m · IQ2_M · ollama · 32.5 tok/s hf.co/unsloth/functiongemma-270m-it-GGUF:IQ2_XXSfunctiongemma/270m · IQ2_XXS · ollama · 33.1 tok/s hf.co/unsloth/functiongemma-270m-it-GGUF:IQ3_XXSfunctiongemma/270m · IQ3_XXS · ollama · 32.6 tok/s hf.co/unsloth/functiongemma-270m-it-GGUF:Q4_0functiongemma/270m · Q4_0 · ollama · 37.2 tok/s hf.co/unsloth/functiongemma-270m-it-GGUF:Q4_K_Mfunctiongemma/270m · Q4_K_M · ollama · 33.8 tok/s hf.co/unsloth/functiongemma-270m-it-GGUF:Q8_0functiongemma/270m · Q8_0 · ollama · 32.9 tok/s hf.co/unsloth/gemma-3-270m-it-GGUF:IQ2_Mgemma-3/270m · IQ2_M · ollama · 34.8 tok/s hf.co/unsloth/gemma-3-270m-it-GGUF:IQ2_XXSgemma-3/270m · IQ2_XXS · ollama · 34.5 tok/s hf.co/unsloth/gemma-3-270m-it-GGUF:IQ3_XXSgemma-3/270m · IQ3_XXS · ollama · 33.4 tok/s hf.co/unsloth/gemma-3-270m-it-GGUF:Q4_0gemma-3/270m · Q4_0 · ollama · 33.0 tok/s hf.co/unsloth/gemma-3-270m-it-GGUF:Q4_K_Mgemma-3/270m · Q4_K_M · ollama · 37.4 tok/s hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ1_Sllama-3-2/3b · IQ1_S · ollama · 225.2 tok/s hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ2_XXSllama-3-2/3b · IQ2_XXS · ollama · 124.2 tok/s hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:IQ3_XXSllama-3-2/3b · IQ3_XXS · ollama · 199.5 tok/s hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q4_0llama-3-2/3b · Q4_0 · ollama · 205.1 tok/s hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q4_K_Mllama-3-2/3b · Q4_K_M · ollama · 203.9 tok/s hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q8_0llama-3-2/3b · Q8_0 · ollama · 72.8 tok/s hf.co/unsloth/Phi-4-mini-instruct-GGUF:Q2_Kphi-4/mini · Q2_K · ollama · 71.0 tok/s hf.co/unsloth/Phi-4-mini-reasoning-GGUF:IQ1_Sphi-4/mini-reasoning · IQ1_S · ollama · 188.9 tok/s hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q2_Kphi-4/mini-reasoning · Q2_K · ollama · 37.7 tok/s hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q2_K_Lphi-4/mini-reasoning · Q2_K_L · ollama · 6.8 tok/s hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q3_K_Mphi-4/mini-reasoning · Q3_K_M · ollama · 31.9 tok/s hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q4_K_Mphi-4/mini-reasoning · Q4_K_M · ollama · 6.5 tok/s hf.co/unsloth/Qwen3-4B-GGUF:IQ1_Sqwen-3/4b · IQ1_S · ollama · 90.4 tok/s hf.co/unsloth/Qwen3-4B-GGUF:Q4_1qwen-3/4b · Q4_1 · ollama · 19.4 tok/s hf.co/unsloth/Qwen3-VL-4B-Instruct-GGUF:Q2_Kqwen-3/4b · Q2_K · ollama · 11.9 tok/s hf.co/unsloth/Qwen3.5-0.8B-GGUF:Q4_0qwen-3-5/0.8b · Q4_0 · ollama · 16.6 tok/s hf.co/unsloth/Qwen3.5-0.8B-GGUF:Q4_K_Mqwen-3-5/0.8b · Q4_K_M · ollama · 17.0 tok/s hf.co/unsloth/Qwen3.5-0.8B-GGUF:Q8_0qwen-3-5/0.8b · Q8_0 · ollama · 12.7 tok/s hf.co/unsloth/Qwen3.5-2B-GGUF:Q4_0qwen-3-5/2b · Q4_0 · ollama · 7.5 tok/s hf.co/unsloth/Qwen3.5-2B-GGUF:Q4_K_Mqwen-3-5/2b · Q4_K_M · ollama · 8.6 tok/s hf.co/unsloth/Qwen3.5-2B-GGUF:Q8_0qwen-3-5/2b · Q8_0 · ollama · 5.7 tok/s

derivatives — changes this publisher made to someone else's weightsDeepSeek-OCRdeepseek-ocr DeepSeek-OCR-2deepseek-ocr-2 DeepSeek-V3.1deepseek-v3-1 DeepSeek-V3.1-Terminusdeepseek-v3-1 Qwen3.5-9Bdeepseek-v4 Devstral-Small-2507devstral-small Devstral-Small-2507-unsloth-bnb-4bitdevstral-small diffusiongemma-26B-A4B-it-GGUFdiffusiongemma embeddinggemma-300m-qat-q8_0-unquantizedembeddinggemma embeddinggemma-2embeddinggemma-2 functiongemma-270m-itfunctiongemma GLM-4.7-Flashglm-4-7 gpt-oss-20b-unsloth-bnb-4bitgpt-oss granite-4.0-1bgranite-4-0 granite-4.0-350mgranite-4-0 granite-4.0-micro-unsloth-bnb-4bitgranite-4-0 granite-4.1-3bgranite-4-1 Kimi-K3-GGUFkimi-k3 LFM2.5-1.2B-Instructlfm-2-5 LFM2.5-230Mlfm-2-5 LFM2.5-24B-A2Blfm-2-5 Llama-3.2-1B-Instructllama-3-2 Llama-3.2-3B-Instructllama-3-2 Magistral-Small-2507magistral-small Magistral-Small-2506magistral-small Magistral-Small-2509-unsloth-bnb-4bitmagistral-small medgemma-1.5-4b-itmedgemma-1-5 Ministral-3-14B-Instruct-2512-bnb-4bitministral-3 Muse-Glimmer-30Bmuse-glimmer Muse-Spark-Open-816B-A42Bmuse-spark North-Mini-Code-1.0north-1 Phi-4-mini-instructphi-4 Qwen3.6-35B-A3B-NVFP4-Fastqwen-3-6 Qwen3.6-35B-A3B-MTP-GGUFqwen-3-6 SmolLM3-3Bsmollm-3 SmolLM3-3B-128K-GGUFsmollm-3

in the catalog, not yet measured — declared, unsignedunsloth/DeepSeek-OCRdeepseek-ocr/base~unsloth · BF16 · vllm · derivative unsloth/DeepSeek-OCR-2deepseek-ocr-2/base~unsloth · BF16 · vllm · derivative unsloth/DeepSeek-V3.1-GGUF:IQ1_Sdeepseek-v3-1/base · IQ1_S · llamacpp · quantizer unsloth/DeepSeek-V3.1-GGUF:IQ2_XXSdeepseek-v3-1/base · IQ2_XXS · llamacpp · quantizer unsloth/DeepSeek-V3.1-GGUF:IQ3_XXSdeepseek-v3-1/base · IQ3_XXS · llamacpp · quantizer unsloth/DeepSeek-V3.1-GGUF:Q4_0deepseek-v3-1/base · Q4_0 · llamacpp · quantizer unsloth/DeepSeek-V3.1-GGUF:Q4_K_Mdeepseek-v3-1/base · Q4_K_M · llamacpp · quantizer unsloth/DeepSeek-V3.1-GGUF:Q8_0deepseek-v3-1/base · Q8_0 · llamacpp · quantizer unsloth/DeepSeek-V3.1-GGUF:BF16deepseek-v3-1/base · BF16 · llamacpp · quantizer unsloth/DeepSeek-V3.1-Terminus-GGUF:IQ1_Sdeepseek-v3-1/terminus · IQ1_S · llamacpp · quantizer unsloth/DeepSeek-V3.1-Terminus-GGUF:IQ2_XXSdeepseek-v3-1/terminus · IQ2_XXS · llamacpp · quantizer unsloth/DeepSeek-V3.1-Terminus-GGUF:IQ3_XXSdeepseek-v3-1/terminus · IQ3_XXS · llamacpp · quantizer unsloth/DeepSeek-V3.1-Terminus-GGUF:Q4_0deepseek-v3-1/terminus · Q4_0 · llamacpp · quantizer unsloth/DeepSeek-V3.1-Terminus-GGUF:Q4_K_Mdeepseek-v3-1/terminus · Q4_K_M · llamacpp · quantizer unsloth/DeepSeek-V3.1-Terminus-GGUF:Q8_0deepseek-v3-1/terminus · Q8_0 · llamacpp · quantizer unsloth/DeepSeek-V3.1-Terminus-GGUF:BF16deepseek-v3-1/terminus · BF16 · llamacpp · quantizer unsloth/DeepSeek-V3.2-GGUF:IQ1_Sdeepseek-v3-2/base · IQ1_S · llamacpp · quantizer unsloth/DeepSeek-V3.2-GGUF:IQ2_XXSdeepseek-v3-2/base · IQ2_XXS · llamacpp · quantizer unsloth/DeepSeek-V3.2-GGUF:IQ3_XXSdeepseek-v3-2/base · IQ3_XXS · llamacpp · quantizer unsloth/DeepSeek-V3.2-GGUF:Q4_0deepseek-v3-2/base · Q4_0 · llamacpp · quantizer unsloth/DeepSeek-V3.2-GGUF:Q4_K_Mdeepseek-v3-2/base · Q4_K_M · llamacpp · quantizer unsloth/DeepSeek-V3.2-GGUF:Q8_0deepseek-v3-2/base · Q8_0 · llamacpp · quantizer unsloth/DeepSeek-V3.2-GGUF:BF16deepseek-v3-2/base · BF16 · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-GGUF:IQ1_Sdeepseek-v4/flash · IQ1_S · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-GGUF:IQ2_XXSdeepseek-v4/flash · IQ2_XXS · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-GGUF:IQ3_XXSdeepseek-v4/flash · IQ3_XXS · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-GGUF:Q4_K_XLdeepseek-v4/flash · Q4_K_XL · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-0731-GGUF:IQ1_Sdeepseek-v4/flash-0731 · IQ1_S · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-0731-GGUF:IQ2_XXSdeepseek-v4/flash-0731 · IQ2_XXS · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-0731-GGUF:IQ3_XXSdeepseek-v4/flash-0731 · IQ3_XXS · llamacpp · quantizer unsloth/DeepSeek-V4-Flash-0731-GGUF:Q4_K_XLdeepseek-v4/flash-0731 · Q4_K_XL · llamacpp · quantizer unsloth/DeepSeek-V4-Pro-0813-GGUF:Q4_K_XLdeepseek-v4/pro-0813 · Q4_K_XL · llamacpp · quantizer unsloth/DeepSeek-V4-Pro-0813-GGUF:Q8_K_XLdeepseek-v4/pro-0813 · Q8_K_XL · llamacpp · quantizer unsloth/DeepSeek-V4.1-Flash-1017-GGUF:IQ1_Sdeepseek-v4-1/flash-1017 · IQ1_S · llamacpp · quantizer unsloth/DeepSeek-V4.1-Flash-1017-GGUF:IQ2_XXSdeepseek-v4-1/flash-1017 · IQ2_XXS · llamacpp · quantizer unsloth/DeepSeek-V4.1-Flash-1017-GGUF:IQ3_XXSdeepseek-v4-1/flash-1017 · IQ3_XXS · llamacpp · quantizer unsloth/DeepSeek-V4.1-Flash-1017-GGUF:Q4_K_XLdeepseek-v4-1/flash-1017 · Q4_K_XL · llamacpp · quantizer hf.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF:IQ1_Sdevstral-2/123b-instruct-2512 · IQ1_S · ollama · quantizer hf.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF:IQ2_XXSdevstral-2/123b-instruct-2512 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF:IQ3_XXSdevstral-2/123b-instruct-2512 · IQ3_XXS · ollama · quantizer unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q3_K_Sdevstral-2/123b-instruct-2512 · Q3_K_S · llamacpp · quantizer unsloth/Devstral-2-123B-Instruct-2512-GGUF:IQ4_XSdevstral-2/123b-instruct-2512 · IQ4_XS · llamacpp · quantizer unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q4_0devstral-2/123b-instruct-2512 · Q4_0 · llamacpp · quantizer unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q4_K_Mdevstral-2/123b-instruct-2512 · Q4_K_M · llamacpp · quantizer unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q8_0devstral-2/123b-instruct-2512 · Q8_0 · llamacpp · quantizer unsloth/Devstral-2-123B-Instruct-2512-GGUF:BF16devstral-2/123b-instruct-2512 · BF16 · llamacpp · quantizer unsloth/Devstral-Small-2507devstral-small/24b-instruct-2503~unsloth-2507 · BF16 · vllm · derivative hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:IQ1_Sdevstral-small/24b-instruct-2512 · IQ1_S · ollama · quantizer hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:IQ2_XXSdevstral-small/24b-instruct-2512 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:IQ3_XXSdevstral-small/24b-instruct-2512 · IQ3_XXS · ollama · quantizer hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_0devstral-small/24b-instruct-2512 · Q4_0 · ollama · quantizer hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q4_K_Mdevstral-small/24b-instruct-2512 · Q4_K_M · ollama · quantizer hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q8_0devstral-small/24b-instruct-2512 · Q8_0 · ollama · quantizer hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:BF16devstral-small/24b-instruct-2512 · BF16 · ollama · quantizer unsloth/Devstral-Small-2-24B-Instruct-2512devstral-small/24b-instruct-2512 · FP8 · vllm · quantizer hf.co/unsloth/Devstral-Small-2505-GGUF:IQ1_Sdevstral-small/2505 · IQ1_S · ollama · quantizer hf.co/unsloth/Devstral-Small-2505-GGUF:IQ2_XXSdevstral-small/2505 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Devstral-Small-2505-GGUF:IQ3_XXSdevstral-small/2505 · IQ3_XXS · ollama · quantizer hf.co/unsloth/Devstral-Small-2505-GGUF:Q4_K_Sdevstral-small/2505 · Q4_K_S · ollama · quantizer hf.co/unsloth/Devstral-Small-2505-GGUF:Q4_K_Mdevstral-small/2505 · Q4_K_M · ollama · quantizer hf.co/unsloth/Devstral-Small-2505-GGUF:Q8_0devstral-small/2505 · Q8_0 · ollama · quantizer hf.co/unsloth/Devstral-Small-2505-GGUF:BF16devstral-small/2505 · BF16 · ollama · quantizer hf.co/unsloth/Devstral-Small-2507-GGUF:IQ1_Sdevstral-small/2507 · IQ1_S · ollama · quantizer hf.co/unsloth/Devstral-Small-2507-GGUF:IQ2_XXSdevstral-small/2507 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Devstral-Small-2507-GGUF:IQ3_XXSdevstral-small/2507 · IQ3_XXS · ollama · quantizer unsloth/Devstral-Small-2507-unsloth-bnb-4bitdevstral-small/2507~unsloth · BITSANDBYTES · vllm · derivative hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q4_K_Mdiffusiongemma/26b-a4b~unsloth · Q4_K_M · ollama · derivative hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q5_K_Mdiffusiongemma/26b-a4b~unsloth · Q5_K_M · ollama · derivative hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:Q8_0diffusiongemma/26b-a4b~unsloth · Q8_0 · ollama · derivative hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:BF16diffusiongemma/26b-a4b~unsloth · BF16 · ollama · derivative unsloth/diffusiongemma-26B-A4B-itdiffusiongemma/26b-a4b~unsloth · BF16 · vllm · derivative unsloth/embeddinggemma-300membeddinggemma/300m · FP32 · vllm · quantizer unsloth/embeddinggemma-300m-qat-q8_0-unquantizedembeddinggemma/300m~unsloth-embeddinggemma-qat-0 · FP32 · vllm · derivative hf.co/unsloth/embeddinggemma-2-GGUF:Q4_K_XLembeddinggemma-2/base · Q4_K_XL · ollama · quantizer hf.co/unsloth/embeddinggemma-2-GGUF:Q8_0embeddinggemma-2/base · Q8_0 · ollama · quantizer hf.co/unsloth/embeddinggemma-2-GGUF:BF16embeddinggemma-2/base · BF16 · ollama · quantizer hf.co/unsloth/embeddinggemma-2-GGUF:F16embeddinggemma-2/base · F16 · ollama · quantizer unsloth/embeddinggemma-2embeddinggemma-2/base~unsloth · BF16 · vllm · derivative hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:IQ1_Sernie-4-5/21b-a3b · IQ1_S · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:IQ2_XXSernie-4-5/21b-a3b · IQ2_XXS · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:IQ3_XXSernie-4-5/21b-a3b · IQ3_XXS · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:Q4_0ernie-4-5/21b-a3b · Q4_0 · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:Q4_K_Mernie-4-5/21b-a3b · Q4_K_M · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:Q8_0ernie-4-5/21b-a3b · Q8_0 · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:BF16ernie-4-5/21b-a3b · BF16 · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:IQ1_Sernie-4-5/21b-a3b-thinking · IQ1_S · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:IQ2_XXSernie-4-5/21b-a3b-thinking · IQ2_XXS · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:IQ3_XXSernie-4-5/21b-a3b-thinking · IQ3_XXS · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:Q4_0ernie-4-5/21b-a3b-thinking · Q4_0 · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:Q4_K_Mernie-4-5/21b-a3b-thinking · Q4_K_M · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:Q8_0ernie-4-5/21b-a3b-thinking · Q8_0 · ollama · quantizer hf.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:BF16ernie-4-5/21b-a3b-thinking · BF16 · ollama · quantizer unsloth/FLUX.1-schnellflux-1/schnell · diffusers · quantizer unsloth/FLUX.2-devflux-2/dev · diffusers · quantizer unsloth/FLUX.2-klein-4Bflux-2/klein-4b · diffusers · quantizer unsloth/FLUX.2-klein-base-4Bflux-2/klein-4b-base · diffusers · quantizer unsloth/functiongemma-270m-it-unsloth-bnb-4bitfunctiongemma/270m~unsloth · BITSANDBYTES · vllm · derivative unsloth/functiongemma-270m-itfunctiongemma/270m~unsloth · BF16 · vllm · derivative hf.co/unsloth/gemma-3-12b-it-qat-GGUF:IQ1_Sgemma-3/12b · IQ1_S · ollama · quantizer hf.co/unsloth/gemma-3-12b-it-qat-GGUF:IQ2_XXSgemma-3/12b · IQ2_XXS · ollama · quantizer hf.co/unsloth/gemma-3-12b-it-qat-GGUF:IQ3_XXSgemma-3/12b · IQ3_XXS · ollama · quantizer hf.co/unsloth/gemma-3-12b-it-qat-GGUF:Q4_0gemma-3/12b · Q4_0 · ollama · quantizer hf.co/unsloth/gemma-3-12b-it-qat-GGUF:Q4_K_Mgemma-3/12b · Q4_K_M · ollama · quantizer hf.co/unsloth/gemma-3-12b-it-qat-GGUF:Q8_0gemma-3/12b · Q8_0 · ollama · quantizer hf.co/unsloth/gemma-3-12b-it-qat-GGUF:BF16gemma-3/12b · BF16 · ollama · quantizer hf.co/unsloth/gemma-3-4b-it-GGUF:IQ1_Sgemma-3/4b · IQ1_S · ollama · quantizer hf.co/unsloth/gemma-3-4b-it-GGUF:IQ2_XXSgemma-3/4b · IQ2_XXS · ollama · quantizer hf.co/unsloth/gemma-3-4b-it-GGUF:IQ3_XXSgemma-3/4b · IQ3_XXS · ollama · quantizer hf.co/unsloth/gemma-3-4b-it-GGUF:Q4_0gemma-3/4b · Q4_0 · ollama · quantizer hf.co/unsloth/gemma-3-4b-it-GGUF:Q4_K_Mgemma-3/4b · Q4_K_M · ollama · quantizer hf.co/unsloth/gemma-3-4b-it-GGUF:Q8_0gemma-3/4b · Q8_0 · ollama · quantizer hf.co/unsloth/gemma-3-4b-it-GGUF:BF16gemma-3/4b · BF16 · ollama · quantizer hf.co/unsloth/gemma-4-12b-it-GGUF:IQ2_Mgemma-4/12b · IQ2_M · ollama · quantizer hf.co/unsloth/gemma-4-12b-it-GGUF:IQ3_XXSgemma-4/12b · IQ3_XXS · ollama · quantizer hf.co/unsloth/gemma-4-12B-it-qat-GGUF:Q4_K_Mgemma-4/12b · Q4_K_M · ollama · quantizer hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ2_XXSgemma-4/26b-a4b · IQ2_XXS · ollama · quantizer hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ2_Mgemma-4/26b-a4b · IQ2_M · ollama · quantizer hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:IQ3_XXSgemma-4/26b-a4b · IQ3_XXS · ollama · quantizer hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q4_K_Mgemma-4/26b-a4b · Q4_K_M · ollama · quantizer unsloth/gemma-4-26B-A4B-it-GGUF:BF16gemma-4/26b-a4b · BF16 · llamacpp · quantizer hf.co/unsloth/gemma-4-E2B-it-qat-mobile-GGUF:Q2_K_XLgemma-4/e2b · Q2_K_XL · ollama · quantizer hf.co/unsloth/gemma-4-E2B-it-GGUF:IQ3_XXSgemma-4/e2b · IQ3_XXS · ollama · quantizer hf.co/unsloth/gemma-4-E4B-it-GGUF:IQ2_Mgemma-4/e4b · IQ2_M · ollama · quantizer hf.co/unsloth/gemma-4-E4B-it-GGUF:IQ3_XXSgemma-4/e4b · IQ3_XXS · ollama · quantizer hf.co/unsloth/GLM-4.5-Air-GGUF:IQ1_Sglm-4-5/air · IQ1_S · ollama · quantizer hf.co/unsloth/GLM-4.5-Air-GGUF:IQ2_XXSglm-4-5/air · IQ2_XXS · ollama · quantizer unsloth/GLM-4.5-Air-GGUF:IQ3_XXSglm-4-5/air · IQ3_XXS · llamacpp · quantizer unsloth/GLM-4.5-Air-GGUF:IQ4_XSglm-4-5/air · IQ4_XS · llamacpp · quantizer unsloth/GLM-4.5-Air-GGUF:Q4_0glm-4-5/air · Q4_0 · llamacpp · quantizer unsloth/GLM-4.5-Air-GGUF:Q4_K_Mglm-4-5/air · Q4_K_M · llamacpp · quantizer unsloth/GLM-4.5-Air-GGUF:Q8_0glm-4-5/air · Q8_0 · llamacpp · quantizer unsloth/GLM-4.5-Air-GGUF:BF16glm-4-5/air · BF16 · llamacpp · quantizer unsloth/GLM-4.5-GGUF:IQ1_Sglm-4-5/base · IQ1_S · llamacpp · quantizer unsloth/GLM-4.5-GGUF:IQ2_XXSglm-4-5/base · IQ2_XXS · llamacpp · quantizer unsloth/GLM-4.5-GGUF:IQ3_XXSglm-4-5/base · IQ3_XXS · llamacpp · quantizer unsloth/GLM-4.5-GGUF:Q4_0glm-4-5/base · Q4_0 · llamacpp · quantizer unsloth/GLM-4.5-GGUF:Q4_K_Mglm-4-5/base · Q4_K_M · llamacpp · quantizer unsloth/GLM-4.5-GGUF:Q8_0glm-4-5/base · Q8_0 · llamacpp · quantizer unsloth/GLM-4.5-GGUF:BF16glm-4-5/base · BF16 · llamacpp · quantizer unsloth/GLM-4.6-GGUF:IQ1_Sglm-4-6/base · IQ1_S · llamacpp · quantizer unsloth/GLM-4.6-GGUF:IQ2_XXSglm-4-6/base · IQ2_XXS · llamacpp · quantizer unsloth/GLM-4.6-GGUF:IQ3_XXSglm-4-6/base · IQ3_XXS · llamacpp · quantizer unsloth/GLM-4.6-GGUF:Q4_0glm-4-6/base · Q4_0 · llamacpp · quantizer unsloth/GLM-4.6-GGUF:Q4_K_Mglm-4-6/base · Q4_K_M · llamacpp · quantizer unsloth/GLM-4.6-GGUF:Q8_0glm-4-6/base · Q8_0 · llamacpp · quantizer unsloth/GLM-4.6-GGUF:BF16glm-4-6/base · BF16 · llamacpp · quantizer hf.co/unsloth/GLM-4.6V-GGUF:IQ1_Sglm-4-6/v · IQ1_S · ollama · quantizer hf.co/unsloth/GLM-4.6V-GGUF:IQ2_XXSglm-4-6/v · IQ2_XXS · ollama · quantizer hf.co/unsloth/GLM-4.6V-GGUF:IQ3_XXSglm-4-6/v · IQ3_XXS · ollama · quantizer unsloth/GLM-4.6V-GGUF:Q3_K_Sglm-4-6/v · Q3_K_S · llamacpp · quantizer unsloth/GLM-4.6V-GGUF:IQ4_XSglm-4-6/v · IQ4_XS · llamacpp · quantizer unsloth/GLM-4.6V-GGUF:Q4_0glm-4-6/v · Q4_0 · llamacpp · quantizer unsloth/GLM-4.6V-GGUF:Q4_K_Mglm-4-6/v · Q4_K_M · llamacpp · quantizer unsloth/GLM-4.6V-GGUF:Q8_0glm-4-6/v · Q8_0 · llamacpp · quantizer unsloth/GLM-4.6V-GGUF:BF16glm-4-6/v · BF16 · llamacpp · quantizer hf.co/unsloth/GLM-4.6V-Flash-GGUF:IQ1_Sglm-4-6/v-flash · IQ1_S · ollama · quantizer hf.co/unsloth/GLM-4.6V-Flash-GGUF:IQ2_XXSglm-4-6/v-flash · IQ2_XXS · ollama · quantizer hf.co/unsloth/GLM-4.6V-Flash-GGUF:IQ3_XXSglm-4-6/v-flash · IQ3_XXS · ollama · quantizer hf.co/unsloth/GLM-4.6V-Flash-GGUF:Q4_0glm-4-6/v-flash · Q4_0 · ollama · quantizer hf.co/unsloth/GLM-4.6V-Flash-GGUF:Q4_K_Mglm-4-6/v-flash · Q4_K_M · ollama · quantizer hf.co/unsloth/GLM-4.6V-Flash-GGUF:Q8_0glm-4-6/v-flash · Q8_0 · ollama · quantizer hf.co/unsloth/GLM-4.6V-Flash-GGUF:BF16glm-4-6/v-flash · BF16 · ollama · quantizer hf.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF:IQ1_Sglm-4-7/23b-a3b~cerebras-flash-reap · IQ1_S · ollama · derivative hf.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF:IQ2_XXSglm-4-7/23b-a3b~cerebras-flash-reap · IQ2_XXS · ollama · derivative hf.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF:IQ3_XXSglm-4-7/23b-a3b~cerebras-flash-reap · IQ3_XXS · ollama · derivative hf.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF:Q4_0glm-4-7/23b-a3b~cerebras-flash-reap · Q4_0 · ollama · derivative hf.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF:Q4_K_Mglm-4-7/23b-a3b~cerebras-flash-reap · Q4_K_M · ollama · derivative hf.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF:Q8_0glm-4-7/23b-a3b~cerebras-flash-reap · Q8_0 · ollama · derivative hf.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF:BF16glm-4-7/23b-a3b~cerebras-flash-reap · BF16 · ollama · derivative unsloth/GLM-4.7-GGUF:IQ1_Sglm-4-7/base · IQ1_S · llamacpp · quantizer unsloth/GLM-4.7-GGUF:IQ2_XXSglm-4-7/base · IQ2_XXS · llamacpp · quantizer unsloth/GLM-4.7-GGUF:IQ3_XXSglm-4-7/base · IQ3_XXS · llamacpp · quantizer unsloth/GLM-4.7-GGUF:Q4_0glm-4-7/base · Q4_0 · llamacpp · quantizer unsloth/GLM-4.7-GGUF:Q4_K_Mglm-4-7/base · Q4_K_M · llamacpp · quantizer unsloth/GLM-4.7-GGUF:Q8_0glm-4-7/base · Q8_0 · llamacpp · quantizer unsloth/GLM-4.7-GGUF:BF16glm-4-7/base · BF16 · llamacpp · quantizer hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ1_Sglm-4-7/flash · IQ1_S · ollama · quantizer hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ2_XXSglm-4-7/flash · IQ2_XXS · ollama · quantizer hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ3_XXSglm-4-7/flash · IQ3_XXS · ollama · quantizer hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_0glm-4-7/flash · Q4_0 · ollama · quantizer hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_Mglm-4-7/flash · Q4_K_M · ollama · quantizer hf.co/unsloth/GLM-4.7-Flash-GGUF:Q8_0glm-4-7/flash · Q8_0 · ollama · quantizer unsloth/GLM-4.7-Flash-FP8-Dynamicglm-4-7/flash · FP8 · vllm · quantizer unsloth/GLM-4.7-Flash-GGUF:BF16glm-4-7/flash · BF16 · llamacpp · quantizer unsloth/GLM-4.7-Flashglm-4-7/flash~unsloth · BF16 · vllm · derivative unsloth/GLM-5-GGUF:IQ1_Sglm-5/base · IQ1_S · llamacpp · quantizer unsloth/GLM-5-GGUF:IQ2_XXSglm-5/base · IQ2_XXS · llamacpp · quantizer unsloth/GLM-5-GGUF:IQ3_XXSglm-5/base · IQ3_XXS · llamacpp · quantizer unsloth/GLM-5-GGUF:Q4_0glm-5/base · Q4_0 · llamacpp · quantizer unsloth/GLM-5-GGUF:Q4_K_Mglm-5/base · Q4_K_M · llamacpp · quantizer unsloth/GLM-5-GGUF:Q8_0glm-5/base · Q8_0 · llamacpp · quantizer unsloth/GLM-5-GGUF:BF16glm-5/base · BF16 · llamacpp · quantizer unsloth/GLM-5.1-GGUF:IQ1_Mglm-5-1/base · IQ1_M · llamacpp · quantizer unsloth/GLM-5.1-GGUF:IQ2_XXSglm-5-1/base · IQ2_XXS · llamacpp · quantizer unsloth/GLM-5.1-GGUF:IQ3_XXSglm-5-1/base · IQ3_XXS · llamacpp · quantizer unsloth/GLM-5.1-GGUF:Q4_K_Sglm-5-1/base · Q4_K_S · llamacpp · quantizer unsloth/GLM-5.1-GGUF:Q4_K_Mglm-5-1/base · Q4_K_M · llamacpp · quantizer unsloth/GLM-5.1-GGUF:Q8_0glm-5-1/base · Q8_0 · llamacpp · quantizer unsloth/GLM-5.1-GGUF:BF16glm-5-1/base · BF16 · llamacpp · quantizer unsloth/GLM-5.2-GGUF:IQ1_Sglm-5-2/base · IQ1_S · llamacpp · quantizer unsloth/GLM-5.2-GGUF:IQ2_XXSglm-5-2/base · IQ2_XXS · llamacpp · quantizer unsloth/GLM-5.2-GGUF:IQ3_XXSglm-5-2/base · IQ3_XXS · llamacpp · quantizer unsloth/GLM-5.2-GGUF:Q4_K_Sglm-5-2/base · Q4_K_S · llamacpp · quantizer unsloth/GLM-5.2-GGUF:Q4_K_Mglm-5-2/base · Q4_K_M · llamacpp · quantizer unsloth/GLM-5.2-GGUF:Q8_0glm-5-2/base · Q8_0 · llamacpp · quantizer unsloth/GLM-5.2-GGUF:BF16glm-5-2/base · BF16 · llamacpp · quantizer unsloth/GLM-5.3-GGUF:IQ1_Sglm-5-3/base · IQ1_S · llamacpp · quantizer unsloth/GLM-5.3-GGUF:IQ3_XXSglm-5-3/base · IQ3_XXS · llamacpp · quantizer unsloth/GLM-5.3-GGUF:IQ4_XSglm-5-3/base · IQ4_XS · llamacpp · quantizer unsloth/GLM-5.3-GGUF:Q4_K_XLglm-5-3/base · Q4_K_XL · llamacpp · quantizer unsloth/GLM-5.3-GGUF:Q8_0glm-5-3/base · Q8_0 · llamacpp · quantizer unsloth/GLM-5.3-GGUF:BF16glm-5-3/base · BF16 · llamacpp · quantizer unsloth/GLM-5.3-Flash-GGUF:IQ1_Sglm-5-3/flash · IQ1_S · llamacpp · quantizer unsloth/GLM-5.3-Flash-GGUF:IQ2_XXSglm-5-3/flash · IQ2_XXS · llamacpp · quantizer unsloth/GLM-5.3-Flash-GGUF:IQ3_XXSglm-5-3/flash · IQ3_XXS · llamacpp · quantizer unsloth/GLM-5.3-Flash-GGUF:Q4_K_XLglm-5-3/flash · Q4_K_XL · llamacpp · quantizer unsloth/GLM-5.3-Flash-GGUF:Q8_0glm-5-3/flash · Q8_0 · llamacpp · quantizer unsloth/GLM-5.3-Flash-GGUF:BF16glm-5-3/flash · BF16 · llamacpp · quantizer unsloth/gpt-oss-120b-GGUF:Q3_K_Sgpt-oss/120b · Q3_K_S · llamacpp · quantizer unsloth/gpt-oss-120b-GGUF:Q2_Kgpt-oss/120b · Q2_K · llamacpp · quantizer unsloth/gpt-oss-120b-GGUF:Q4_0gpt-oss/120b · Q4_0 · llamacpp · quantizer unsloth/gpt-oss-120b-GGUF:Q4_K_Mgpt-oss/120b · Q4_K_M · llamacpp · quantizer unsloth/gpt-oss-120b-GGUF:Q8_0gpt-oss/120b · Q8_0 · llamacpp · quantizer unsloth/gpt-oss-120b-GGUF:Q8_K_XLgpt-oss/120b · Q8_K_XL · llamacpp · quantizer hf.co/unsloth/gpt-oss-20b-GGUF:Q3_K_Sgpt-oss/20b · Q3_K_S · ollama · quantizer hf.co/unsloth/gpt-oss-20b-GGUF:Q2_Kgpt-oss/20b · Q2_K · ollama · quantizer hf.co/unsloth/gpt-oss-20b-GGUF:Q4_0gpt-oss/20b · Q4_0 · ollama · quantizer hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_Mgpt-oss/20b · Q4_K_M · ollama · quantizer hf.co/unsloth/gpt-oss-20b-GGUF:Q8_0gpt-oss/20b · Q8_0 · ollama · quantizer hf.co/unsloth/gpt-oss-20b-GGUF:Q8_K_XLgpt-oss/20b · Q8_K_XL · ollama · quantizer hf.co/unsloth/gpt-oss-20b-GGUF:F16gpt-oss/20b · F16 · ollama · quantizer unsloth/gpt-oss-20b-unsloth-bnb-4bitgpt-oss/20b~unsloth · BITSANDBYTES · vllm · derivative unsloth/gpt-oss-20b-BF16gpt-oss/20b~unsloth · BF16 · vllm · derivative unsloth/granite-4.0-1bgranite-4-0/1b~unsloth · BF16 · vllm · derivative hf.co/unsloth/granite-4.0-350m-GGUF:IQ3_XXSgranite-4-0/350m · IQ3_XXS · ollama · quantizer hf.co/unsloth/granite-4.0-350m-GGUF:IQ4_XSgranite-4-0/350m · IQ4_XS · ollama · quantizer hf.co/unsloth/granite-4.0-350m-GGUF:Q4_0granite-4-0/350m · Q4_0 · ollama · quantizer hf.co/unsloth/granite-4.0-350m-GGUF:Q4_K_Sgranite-4-0/350m · Q4_K_S · ollama · quantizer hf.co/unsloth/granite-4.0-350m-GGUF:Q4_K_Mgranite-4-0/350m · Q4_K_M · ollama · quantizer hf.co/unsloth/granite-4.0-350m-GGUF:Q8_0granite-4-0/350m · Q8_0 · ollama · quantizer hf.co/unsloth/granite-4.0-350m-GGUF:BF16granite-4-0/350m · BF16 · ollama · quantizer unsloth/granite-4.0-350mgranite-4-0/350m~unsloth · BF16 · vllm · derivative hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ1_Sgranite-4-0/h-micro · IQ1_S · ollama · quantizer hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ2_XXSgranite-4-0/h-micro · IQ2_XXS · ollama · quantizer hf.co/unsloth/granite-4.0-h-micro-GGUF:IQ3_XXSgranite-4-0/h-micro · IQ3_XXS · ollama · quantizer hf.co/unsloth/granite-4.0-h-micro-GGUF:Q4_0granite-4-0/h-micro · Q4_0 · ollama · quantizer hf.co/unsloth/granite-4.0-h-micro-GGUF:Q4_K_Mgranite-4-0/h-micro · Q4_K_M · ollama · quantizer hf.co/unsloth/granite-4.0-h-micro-GGUF:Q8_0granite-4-0/h-micro · Q8_0 · ollama · quantizer hf.co/unsloth/granite-4.0-h-micro-GGUF:BF16granite-4-0/h-micro · BF16 · ollama · quantizer unsloth/granite-4.0-micro-unsloth-bnb-4bitgranite-4-0/micro~unsloth · BITSANDBYTES · vllm · derivative hf.co/unsloth/granite-4.1-3b-GGUF:IQ2_Mgranite-4-1/3b · IQ2_M · ollama · quantizer hf.co/unsloth/granite-4.1-3b-GGUF:IQ3_XXSgranite-4-1/3b · IQ3_XXS · ollama · quantizer hf.co/unsloth/granite-4.1-3b-GGUF:IQ4_XSgranite-4-1/3b · IQ4_XS · ollama · quantizer hf.co/unsloth/granite-4.1-3b-GGUF:Q4_0granite-4-1/3b · Q4_0 · ollama · quantizer hf.co/unsloth/granite-4.1-3b-GGUF:Q4_K_Mgranite-4-1/3b · Q4_K_M · ollama · quantizer hf.co/unsloth/granite-4.1-3b-GGUF:Q8_0granite-4-1/3b · Q8_0 · ollama · quantizer hf.co/unsloth/granite-4.1-3b-GGUF:BF16granite-4-1/3b · BF16 · ollama · quantizer unsloth/granite-4.1-3bgranite-4-1/3b~unsloth · BF16 · vllm · derivative hf.co/unsloth/Hy-MT2-7B-GGUF:IQ2_Mhy-mt-2/7b · IQ2_M · ollama · quantizer hf.co/unsloth/Hy-MT2-7B-GGUF:IQ3_XXShy-mt-2/7b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Hy-MT2-7B-GGUF:IQ4_XShy-mt-2/7b · IQ4_XS · ollama · quantizer hf.co/unsloth/Hy-MT2-7B-GGUF:BF16hy-mt-2/7b · BF16 · ollama · quantizer unsloth/Kimi-K2-Instruct-GGUF:IQ1_Skimi-k2/base · IQ1_S · llamacpp · quantizer unsloth/Kimi-K2-Instruct-GGUF:IQ2_XXSkimi-k2/base · IQ2_XXS · llamacpp · quantizer unsloth/Kimi-K2-Instruct-GGUF:IQ3_XXSkimi-k2/base · IQ3_XXS · llamacpp · quantizer unsloth/Kimi-K2-Instruct-GGUF:Q4_0kimi-k2/base · Q4_0 · llamacpp · quantizer unsloth/Kimi-K2-Instruct-GGUF:Q4_K_Mkimi-k2/base · Q4_K_M · llamacpp · quantizer unsloth/Kimi-K2-Instruct-GGUF:Q8_0kimi-k2/base · Q8_0 · llamacpp · quantizer unsloth/Kimi-K2-Instruct-GGUF:BF16kimi-k2/base · BF16 · llamacpp · quantizer unsloth/Kimi-K2-Instruct-0905-GGUF:IQ1_Skimi-k2/instruct-0905 · IQ1_S · llamacpp · quantizer unsloth/Kimi-K2-Instruct-0905-GGUF:IQ2_XXSkimi-k2/instruct-0905 · IQ2_XXS · llamacpp · quantizer unsloth/Kimi-K2-Instruct-0905-GGUF:IQ3_XXSkimi-k2/instruct-0905 · IQ3_XXS · llamacpp · quantizer unsloth/Kimi-K2-Instruct-0905-GGUF:Q4_0kimi-k2/instruct-0905 · Q4_0 · llamacpp · quantizer unsloth/Kimi-K2-Instruct-0905-GGUF:Q4_K_Mkimi-k2/instruct-0905 · Q4_K_M · llamacpp · quantizer unsloth/Kimi-K2-Instruct-0905-GGUF:Q8_0kimi-k2/instruct-0905 · Q8_0 · llamacpp · quantizer unsloth/Kimi-K2-Instruct-0905-GGUF:BF16kimi-k2/instruct-0905 · BF16 · llamacpp · quantizer unsloth/Kimi-K2-Thinking-GGUF:IQ1_Skimi-k2/thinking · IQ1_S · llamacpp · quantizer unsloth/Kimi-K2-Thinking-GGUF:IQ2_XXSkimi-k2/thinking · IQ2_XXS · llamacpp · quantizer unsloth/Kimi-K2-Thinking-GGUF:IQ3_XXSkimi-k2/thinking · IQ3_XXS · llamacpp · quantizer unsloth/Kimi-K2-Thinking-GGUF:Q4_0kimi-k2/thinking · Q4_0 · llamacpp · quantizer unsloth/Kimi-K2-Thinking-GGUF:Q4_K_Mkimi-k2/thinking · Q4_K_M · llamacpp · quantizer unsloth/Kimi-K2-Thinking-GGUF:Q8_0kimi-k2/thinking · Q8_0 · llamacpp · quantizer unsloth/Kimi-K2-Thinking-GGUF:BF16kimi-k2/thinking · BF16 · llamacpp · quantizer unsloth/Kimi-K2.5-GGUF:IQ1_Skimi-k2-5/base · IQ1_S · llamacpp · quantizer unsloth/Kimi-K2.5-GGUF:IQ2_XXSkimi-k2-5/base · IQ2_XXS · llamacpp · quantizer unsloth/Kimi-K2.5-GGUF:IQ3_XXSkimi-k2-5/base · IQ3_XXS · llamacpp · quantizer unsloth/Kimi-K2.5-GGUF:Q4_0kimi-k2-5/base · Q4_0 · llamacpp · quantizer unsloth/Kimi-K2.5-GGUF:Q4_K_Mkimi-k2-5/base · Q4_K_M · llamacpp · quantizer unsloth/Kimi-K2.5-GGUF:Q8_0kimi-k2-5/base · Q8_0 · llamacpp · quantizer unsloth/Kimi-K2.5-GGUF:BF16kimi-k2-5/base · BF16 · llamacpp · quantizer unsloth/Kimi-K2.6-GGUF:Q2_K_XLkimi-k2-6/base · Q2_K_XL · llamacpp · quantizer unsloth/Kimi-K2.6-GGUF:Q4_K_XLkimi-k2-6/base · Q4_K_XL · llamacpp · quantizer unsloth/Kimi-K2.6-GGUF:Q8_K_XLkimi-k2-6/base · Q8_K_XL · llamacpp · quantizer unsloth/Kimi-K2.6-GGUF:BF16kimi-k2-6/base · BF16 · llamacpp · quantizer unsloth/Kimi-K2.7-Code-GGUF:IQ1_Mkimi-k2-7/code · IQ1_M · llamacpp · quantizer unsloth/Kimi-K2.7-Code-GGUF:IQ2_XXSkimi-k2-7/code · IQ2_XXS · llamacpp · quantizer unsloth/Kimi-K2.7-Code-GGUF:Q3_K_Mkimi-k2-7/code · Q3_K_M · llamacpp · quantizer unsloth/Kimi-K2.7-Code-GGUF:Q4_K_XLkimi-k2-7/code · Q4_K_XL · llamacpp · quantizer unsloth/Kimi-K2.7-Codekimi-k2-7/code · W4A16 · vllm · quantizer unsloth/Kimi-K3-GGUF:Q1_0kimi-k3/base · Q1_0 · llamacpp · quantizer unsloth/Kimi-K3-GGUF:IQ1_Skimi-k3/base · IQ1_S · llamacpp · quantizer unsloth/Kimi-K3-GGUF:Q4_K_XLkimi-k3/base · Q4_K_XL · llamacpp · quantizer hf.co/unsloth/LFM2.5-1.2B-Instruct-GGUF:Q2_K_XLlfm-2-5/1.2b · Q2_K_XL · ollama · quantizer hf.co/unsloth/LFM2.5-1.2B-Instruct-GGUF:Q3_K_Slfm-2-5/1.2b · Q3_K_S · ollama · quantizer hf.co/unsloth/LFM2.5-1.2B-Instruct-GGUF:Q4_0lfm-2-5/1.2b · Q4_0 · ollama · quantizer hf.co/unsloth/LFM2.5-1.2B-Instruct-GGUF:Q8_0lfm-2-5/1.2b · Q8_0 · ollama · quantizer hf.co/unsloth/LFM2.5-1.2B-Instruct-GGUF:Q8_K_XLlfm-2-5/1.2b · Q8_K_XL · ollama · quantizer hf.co/unsloth/LFM2.5-1.2B-Instruct-GGUF:BF16lfm-2-5/1.2b · BF16 · ollama · quantizer unsloth/LFM2.5-1.2B-Instructlfm-2-5/1.2b~unsloth · BF16 · vllm · derivative unsloth/LFM2.5-230Mlfm-2-5/230m~unsloth · BF16 · vllm · derivative hf.co/unsloth/LFM2.5-24B-A2B-GGUF:IQ2_XXSlfm-2-5/24b-a2b · IQ2_XXS · ollama · quantizer hf.co/unsloth/LFM2.5-24B-A2B-GGUF:IQ2_Mlfm-2-5/24b-a2b · IQ2_M · ollama · quantizer hf.co/unsloth/LFM2.5-24B-A2B-GGUF:IQ3_XXSlfm-2-5/24b-a2b · IQ3_XXS · ollama · quantizer unsloth/LFM2.5-24B-A2Blfm-2-5/24b-a2b~unsloth · BF16 · vllm · derivative hf.co/unsloth/LFM2.5-VL-3B-GGUF:IQ2_Mlfm-2-5/vl-3b · IQ2_M · ollama · quantizer hf.co/unsloth/LFM2.5-VL-3B-GGUF:IQ3_XXSlfm-2-5/vl-3b · IQ3_XXS · ollama · quantizer hf.co/unsloth/LFM2.5-VL-3B-GGUF:IQ4_XSlfm-2-5/vl-3b · IQ4_XS · ollama · quantizer hf.co/unsloth/LFM2.5-VL-3B-GGUF:Q4_0lfm-2-5/vl-3b · Q4_0 · ollama · quantizer hf.co/unsloth/LFM2.5-VL-3B-GGUF:Q4_K_Mlfm-2-5/vl-3b · Q4_K_M · ollama · quantizer hf.co/unsloth/LFM2.5-VL-3B-GGUF:Q8_0lfm-2-5/vl-3b · Q8_0 · ollama · quantizer hf.co/unsloth/LFM2.5-VL-3B-GGUF:BF16lfm-2-5/vl-3b · BF16 · ollama · quantizer unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bitllama-3-2/1b~unsloth-llama-3-2 · BITSANDBYTES · vllm · derivative unsloth/Llama-3.2-1B-Instructllama-3-2/1b~unsloth-llama-3-2 · BF16 · vllm · derivative unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bitllama-3-2/3b~unsloth-llama-3-2 · BITSANDBYTES · vllm · derivative unsloth/Llama-3.2-3B-Instructllama-3-2/3b~unsloth-llama-3-2 · BF16 · vllm · derivative unsloth/LTX-2.5-FP8ltx-2-5/base · FP8 · diffusers · quantizer unsloth/Magistral-Small-2507magistral-small/24b-instruct-2503~unsloth-2507 · BF16 · vllm · derivative hf.co/unsloth/Magistral-Small-2506-GGUF:IQ2_XXSmagistral-small/2506 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Magistral-Small-2506-GGUF:IQ2_Mmagistral-small/2506 · IQ2_M · ollama · quantizer hf.co/unsloth/Magistral-Small-2506-GGUF:IQ3_XXSmagistral-small/2506 · IQ3_XXS · ollama · quantizer hf.co/unsloth/Magistral-Small-2506-GGUF:Q4_0magistral-small/2506 · Q4_0 · ollama · quantizer hf.co/unsloth/Magistral-Small-2506-GGUF:Q4_K_Mmagistral-small/2506 · Q4_K_M · ollama · quantizer hf.co/unsloth/Magistral-Small-2506-GGUF:BF16magistral-small/2506 · BF16 · ollama · quantizer unsloth/Magistral-Small-2506-unsloth-bnb-4bitmagistral-small/2506~unsloth · BITSANDBYTES · vllm · derivative unsloth/Magistral-Small-2506magistral-small/2506~unsloth · BF16 · vllm · derivative hf.co/unsloth/Magistral-Small-2509-GGUF:IQ2_XXSmagistral-small/2509 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Magistral-Small-2509-GGUF:IQ2_Mmagistral-small/2509 · IQ2_M · ollama · quantizer hf.co/unsloth/Magistral-Small-2509-GGUF:IQ3_XXSmagistral-small/2509 · IQ3_XXS · ollama · quantizer unsloth/Magistral-Small-2509-FP8-Dynamicmagistral-small/2509 · FP8 · vllm · quantizer unsloth/Magistral-Small-2509-unsloth-bnb-4bitmagistral-small/2509~unsloth · BITSANDBYTES · vllm · derivative unsloth/Magistral-Small-2509magistral-small/2509~unsloth · BF16 · vllm · derivative hf.co/unsloth/medgemma-1.5-4b-it-GGUF:IQ1_Smedgemma-1-5/4b · IQ1_S · ollama · quantizer hf.co/unsloth/medgemma-1.5-4b-it-GGUF:IQ2_XXSmedgemma-1-5/4b · IQ2_XXS · ollama · quantizer hf.co/unsloth/medgemma-1.5-4b-it-GGUF:IQ3_XXSmedgemma-1-5/4b · IQ3_XXS · ollama · quantizer hf.co/unsloth/medgemma-1.5-4b-it-GGUF:Q4_0medgemma-1-5/4b · Q4_0 · ollama · quantizer hf.co/unsloth/medgemma-1.5-4b-it-GGUF:Q4_K_Mmedgemma-1-5/4b · Q4_K_M · ollama · quantizer hf.co/unsloth/medgemma-1.5-4b-it-GGUF:Q8_0medgemma-1-5/4b · Q8_0 · ollama · quantizer hf.co/unsloth/medgemma-1.5-4b-it-GGUF:BF16medgemma-1-5/4b · BF16 · ollama · quantizer unsloth/medgemma-1.5-4b-it-unsloth-bnb-4bitmedgemma-1-5/4b~unsloth · BITSANDBYTES · vllm · derivative unsloth/medgemma-1.5-4b-itmedgemma-1-5/4b~unsloth · BF16 · vllm · derivative unsloth/MiMo-V2-Flash-GGUF:IQ1_Smimo-v2/flash · IQ1_S · llamacpp · quantizer unsloth/MiMo-V2-Flash-GGUF:IQ2_XXSmimo-v2/flash · IQ2_XXS · llamacpp · quantizer unsloth/MiMo-V2-Flash-GGUF:IQ3_XXSmimo-v2/flash · IQ3_XXS · llamacpp · quantizer unsloth/MiMo-V2-Flash-GGUF:Q4_0mimo-v2/flash · Q4_0 · llamacpp · quantizer unsloth/MiMo-V2-Flash-GGUF:Q4_K_Mmimo-v2/flash · Q4_K_M · llamacpp · quantizer unsloth/MiMo-V2-Flash-GGUF:Q8_0mimo-v2/flash · Q8_0 · llamacpp · quantizer unsloth/MiMo-V2-Flash-GGUF:BF16mimo-v2/flash · BF16 · llamacpp · quantizer unsloth/MiMo-V2.5-GGUF:IQ1_Mmimo-v2-5/base · IQ1_M · llamacpp · quantizer unsloth/MiMo-V2.5-GGUF:IQ2_XXSmimo-v2-5/base · IQ2_XXS · llamacpp · quantizer unsloth/MiMo-V2.5-GGUF:IQ3_XXSmimo-v2-5/base · IQ3_XXS · llamacpp · quantizer unsloth/MiMo-V2.5-GGUF:Q4_K_Smimo-v2-5/base · Q4_K_S · llamacpp · quantizer unsloth/MiMo-V2.5-GGUF:Q4_K_Mmimo-v2-5/base · Q4_K_M · llamacpp · quantizer unsloth/MiMo-V2.5-GGUF:Q8_0mimo-v2-5/base · Q8_0 · llamacpp · quantizer unsloth/MiMo-V2.5-GGUF:BF16mimo-v2-5/base · BF16 · llamacpp · quantizer unsloth/MiMo-V2.5-Pro-GGUF:IQ1_Mmimo-v2-5/pro · IQ1_M · llamacpp · quantizer unsloth/MiMo-V2.5-Pro-GGUF:IQ2_XXSmimo-v2-5/pro · IQ2_XXS · llamacpp · quantizer unsloth/MiMo-V2.5-Pro-GGUF:IQ3_XXSmimo-v2-5/pro · IQ3_XXS · llamacpp · quantizer unsloth/MiMo-V2.5-Pro-GGUF:Q4_K_Smimo-v2-5/pro · Q4_K_S · llamacpp · quantizer unsloth/MiMo-V2.5-Pro-GGUF:Q4_K_Mmimo-v2-5/pro · Q4_K_M · llamacpp · quantizer unsloth/MiMo-V2.5-Pro-GGUF:Q8_0mimo-v2-5/pro · Q8_0 · llamacpp · quantizer unsloth/MiMo-V2.5-Pro-GGUF:BF16mimo-v2-5/pro · BF16 · llamacpp · quantizer unsloth/MiniMax-M2-GGUF:IQ1_Sminimax-m2/base · IQ1_S · llamacpp · quantizer unsloth/MiniMax-M2-GGUF:IQ2_XXSminimax-m2/base · IQ2_XXS · llamacpp · quantizer unsloth/MiniMax-M2-GGUF:IQ3_XXSminimax-m2/base · IQ3_XXS · llamacpp · quantizer unsloth/MiniMax-M2-GGUF:Q4_0minimax-m2/base · Q4_0 · llamacpp · quantizer unsloth/MiniMax-M2-GGUF:Q4_K_Mminimax-m2/base · Q4_K_M · llamacpp · quantizer unsloth/MiniMax-M2-GGUF:Q8_0minimax-m2/base · Q8_0 · llamacpp · quantizer unsloth/MiniMax-M2-GGUF:BF16minimax-m2/base · BF16 · llamacpp · quantizer unsloth/MiniMax-M2.1-GGUF:IQ1_Sminimax-m2-1/base · IQ1_S · llamacpp · quantizer unsloth/MiniMax-M2.1-GGUF:IQ2_XXSminimax-m2-1/base · IQ2_XXS · llamacpp · quantizer unsloth/MiniMax-M2.1-GGUF:IQ3_XXSminimax-m2-1/base · IQ3_XXS · llamacpp · quantizer unsloth/MiniMax-M2.1-GGUF:Q4_0minimax-m2-1/base · Q4_0 · llamacpp · quantizer unsloth/MiniMax-M2.1-GGUF:Q4_K_Mminimax-m2-1/base · Q4_K_M · llamacpp · quantizer unsloth/MiniMax-M2.1-GGUF:Q8_0minimax-m2-1/base · Q8_0 · llamacpp · quantizer unsloth/MiniMax-M2.1-GGUF:BF16minimax-m2-1/base · BF16 · llamacpp · quantizer unsloth/MiniMax-M2.5-GGUF:IQ1_Sminimax-m2-5/base · IQ1_S · llamacpp · quantizer unsloth/MiniMax-M2.5-GGUF:IQ2_XXSminimax-m2-5/base · IQ2_XXS · llamacpp · quantizer unsloth/MiniMax-M2.5-GGUF:IQ3_XXSminimax-m2-5/base · IQ3_XXS · llamacpp · quantizer unsloth/MiniMax-M2.5-GGUF:Q4_0minimax-m2-5/base · Q4_0 · llamacpp · quantizer unsloth/MiniMax-M2.5-GGUF:Q4_K_Mminimax-m2-5/base · Q4_K_M · llamacpp · quantizer unsloth/MiniMax-M2.5-GGUF:Q8_0minimax-m2-5/base · Q8_0 · llamacpp · quantizer unsloth/MiniMax-M2.5-GGUF:BF16minimax-m2-5/base · BF16 · llamacpp · quantizer unsloth/MiniMax-M2.7-GGUF:BF16minimax-m2-7/base · BF16 · llamacpp · quantizer unsloth/MiniMax-M3-GGUF:IQ1_Mminimax-m3/base · IQ1_M · llamacpp · quantizer unsloth/MiniMax-M3-GGUF:IQ2_XXSminimax-m3/base · IQ2_XXS · llamacpp · quantizer unsloth/MiniMax-M3-GGUF:IQ3_XXSminimax-m3/base · IQ3_XXS · llamacpp · quantizer unsloth/MiniMax-M3-GGUF:Q4_K_Sminimax-m3/base · Q4_K_S · llamacpp · quantizer unsloth/MiniMax-M3-GGUF:Q4_K_Mminimax-m3/base · Q4_K_M · llamacpp · quantizer unsloth/MiniMax-M3-GGUF:Q8_0minimax-m3/base · Q8_0 · llamacpp · quantizer unsloth/MiniMax-M3-GGUF:BF16minimax-m3/base · BF16 · llamacpp · quantizer unsloth/MiniMax-M3.1-Flash-GGUF:IQ3_XXSminimax-m3-1/flash · IQ3_XXS · llamacpp · quantizer unsloth/MiniMax-M3.1-Flash-GGUF:Q4_K_XLminimax-m3-1/flash · Q4_K_XL · llamacpp · quantizer unsloth/Ministral-3-14B-Instruct-2512-bnb-4bitministral-3/14b-instruct-2512~unsloth · BITSANDBYTES · vllm · derivative hf.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF:IQ1_Sministral-3/3b-instruct-2512 · IQ1_S · ollama · quantizer hf.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF:IQ2_XXSministral-3/3b-instruct-2512 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF:IQ3_XXSministral-3/3b-instruct-2512 · IQ3_XXS · ollama · quantizer unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:IQ1_Smistral-large-3/675b-instruct-2512 · IQ1_S · llamacpp · quantizer unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:IQ2_XXSmistral-large-3/675b-instruct-2512 · IQ2_XXS · llamacpp · quantizer unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:IQ3_XXSmistral-large-3/675b-instruct-2512 · IQ3_XXS · llamacpp · quantizer unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_0mistral-large-3/675b-instruct-2512 · Q4_0 · llamacpp · quantizer unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_K_Mmistral-large-3/675b-instruct-2512 · Q4_K_M · llamacpp · quantizer unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q8_0mistral-large-3/675b-instruct-2512 · Q8_0 · llamacpp · quantizer unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:BF16mistral-large-3/675b-instruct-2512 · BF16 · llamacpp · quantizer hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:IQ2_XXSmistral-medium-3-5/128b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:IQ2_Mmistral-medium-3-5/128b · IQ2_M · ollama · quantizer hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:IQ3_XXSmistral-medium-3-5/128b · IQ3_XXS · ollama · quantizer unsloth/Mistral-Medium-3.5-128B-GGUF:Q3_K_Smistral-medium-3-5/128b · Q3_K_S · llamacpp · quantizer unsloth/Mistral-Medium-3.5-128B-GGUF:IQ4_XSmistral-medium-3-5/128b · IQ4_XS · llamacpp · quantizer unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_0mistral-medium-3-5/128b · Q4_0 · llamacpp · quantizer unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_K_Mmistral-medium-3-5/128b · Q4_K_M · llamacpp · quantizer unsloth/Mistral-Medium-3.5-128B-GGUF:Q8_0mistral-medium-3-5/128b · Q8_0 · llamacpp · quantizer unsloth/Mistral-Medium-3.5-128B-GGUF:BF16mistral-medium-3-5/128b · BF16 · llamacpp · quantizer hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:IQ1_Mmistral-small-4/119b-2603 · IQ1_M · ollama · quantizer hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:IQ2_XXSmistral-small-4/119b-2603 · IQ2_XXS · ollama · quantizer hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF:IQ3_XXSmistral-small-4/119b-2603 · IQ3_XXS · ollama · quantizer unsloth/Mistral-Small-4-119B-2603-GGUF:Q3_K_Mmistral-small-4/119b-2603 · Q3_K_M · llamacpp · quantizer unsloth/Mistral-Small-4-119B-2603-GGUF:IQ4_XSmistral-small-4/119b-2603 · IQ4_XS · llamacpp · quantizer unsloth/Mistral-Small-4-119B-2603-GGUF:Q4_K_Smistral-small-4/119b-2603 · Q4_K_S · llamacpp · quantizer unsloth/Mistral-Small-4-119B-2603-GGUF:Q4_K_Mmistral-small-4/119b-2603 · Q4_K_M · llamacpp · quantizer unsloth/Mistral-Small-4-119B-2603-GGUF:Q8_0mistral-small-4/119b-2603 · Q8_0 · llamacpp · quantizer unsloth/Mistral-Small-4-119B-2603-GGUF:BF16mistral-small-4/119b-2603 · BF16 · llamacpp · quantizer hf.co/unsloth/Muse-Glimmer-30B-GGUF:IQ2_XXSmuse-glimmer/30b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Muse-Glimmer-30B-GGUF:IQ2_XSmuse-glimmer/30b · IQ2_XS · ollama · quantizer hf.co/unsloth/Muse-Glimmer-30B-GGUF:IQ3_XXSmuse-glimmer/30b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Muse-Glimmer-30B-GGUF:Q8_0muse-glimmer/30b · Q8_0 · ollama · quantizer unsloth/Muse-Glimmer-30B-GGUF:BF16muse-glimmer/30b · BF16 · llamacpp · quantizer unsloth/Muse-Glimmer-30B-unsloth-bnb-4bitmuse-glimmer/30b~unsloth · BITSANDBYTES · vllm · derivative unsloth/Muse-Glimmer-30Bmuse-glimmer/30b~unsloth · BF16 · vllm · derivative unsloth/Muse-Spark-Open-816B-A42B-GGUF:IQ1_Smuse-spark/816b-a42b · IQ1_S · llamacpp · quantizer unsloth/Muse-Spark-Open-816B-A42B-GGUF:IQ2_XXSmuse-spark/816b-a42b · IQ2_XXS · llamacpp · quantizer unsloth/Muse-Spark-Open-816B-A42B-GGUF:IQ3_XXSmuse-spark/816b-a42b · IQ3_XXS · llamacpp · quantizer unsloth/Muse-Spark-Open-816B-A42B-GGUF:Q4_K_XLmuse-spark/816b-a42b · Q4_K_XL · llamacpp · quantizer unsloth/Muse-Spark-Open-816B-A42B-NVFP4muse-spark/816b-a42b · NVFP4 · vllm · quantizer unsloth/Muse-Spark-Open-816B-A42Bmuse-spark/816b-a42b~unsloth-open · BF16 · vllm · derivative hf.co/unsloth/North-Mini-Code-1.0-GGUF:IQ1_Mnorth-1/mini-code-1-0 · IQ1_M · ollama · quantizer hf.co/unsloth/North-Mini-Code-1.0-GGUF:IQ2_XXSnorth-1/mini-code-1-0 · IQ2_XXS · ollama · quantizer hf.co/unsloth/North-Mini-Code-1.0-GGUF:IQ3_XXSnorth-1/mini-code-1-0 · IQ3_XXS · ollama · quantizer hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q4_K_Snorth-1/mini-code-1-0 · Q4_K_S · ollama · quantizer hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q4_K_Mnorth-1/mini-code-1-0 · Q4_K_M · ollama · quantizer hf.co/unsloth/North-Mini-Code-1.0-GGUF:Q8_0north-1/mini-code-1-0 · Q8_0 · ollama · quantizer unsloth/North-Mini-Code-1.0-GGUF:BF16north-1/mini-code-1-0 · BF16 · llamacpp · quantizer unsloth/North-Mini-Code-1.0north-1/mini-code-1-0~unsloth · BF16 · vllm · derivative hf.co/unsloth/Phi-4-mini-reasoning-GGUF:IQ2_XXSphi-4/mini-reasoning · IQ2_XXS · ollama · quantizer hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q4_0phi-4/mini-reasoning · Q4_0 · ollama · quantizer hf.co/unsloth/Phi-4-mini-reasoning-GGUF:Q8_0phi-4/mini-reasoning · Q8_0 · ollama · quantizer hf.co/unsloth/Phi-4-mini-reasoning-GGUF:BF16phi-4/mini-reasoning · BF16 · ollama · quantizer unsloth/Phi-4-mini-instruct-unsloth-bnb-4bitphi-4/mini~unsloth · BITSANDBYTES · vllm · derivative unsloth/Phi-4-mini-instructphi-4/mini~unsloth · BF16 · vllm · derivative hf.co/unsloth/Phi-4-reasoning-plus-GGUF:IQ1_Sphi-4/reasoning-plus · IQ1_S · ollama · quantizer hf.co/unsloth/Phi-4-reasoning-plus-GGUF:IQ2_XXSphi-4/reasoning-plus · IQ2_XXS · ollama · quantizer hf.co/unsloth/Phi-4-reasoning-plus-GGUF:IQ3_XXSphi-4/reasoning-plus · IQ3_XXS · ollama · quantizer hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q4_0phi-4/reasoning-plus · Q4_0 · ollama · quantizer hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q8_0phi-4/reasoning-plus · Q8_0 · ollama · quantizer hf.co/unsloth/Phi-4-reasoning-plus-GGUF:BF16phi-4/reasoning-plus · BF16 · ollama · quantizer hf.co/unsloth/Qwen3.5-0.8B-GGUF:IQ2_XXSqwen-3-5/0.8b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-0.8B-GGUF:IQ2_Mqwen-3-5/0.8b · IQ2_M · ollama · quantizer hf.co/unsloth/Qwen3.5-0.8B-GGUF:IQ3_XXSqwen-3-5/0.8b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-0.8B-GGUF:BF16qwen-3-5/0.8b · BF16 · ollama · quantizer hf.co/unsloth/Qwen3.5-27B-GGUF:IQ2_XXSqwen-3-5/27b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-27B-GGUF:IQ2_Mqwen-3-5/27b · IQ2_M · ollama · quantizer hf.co/unsloth/Qwen3.5-27B-GGUF:IQ3_XXSqwen-3-5/27b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-27B-GGUF:Q4_0qwen-3-5/27b · Q4_0 · ollama · quantizer hf.co/unsloth/Qwen3.5-27B-GGUF:Q4_K_Mqwen-3-5/27b · Q4_K_M · ollama · quantizer hf.co/unsloth/Qwen3.5-27B-GGUF:Q8_0qwen-3-5/27b · Q8_0 · ollama · quantizer unsloth/Qwen3.5-27B-GGUF:BF16qwen-3-5/27b · BF16 · llamacpp · quantizer hf.co/unsloth/Qwen3.5-2B-GGUF:IQ2_XXSqwen-3-5/2b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-2B-GGUF:IQ2_Mqwen-3-5/2b · IQ2_M · ollama · quantizer hf.co/unsloth/Qwen3.5-2B-GGUF:IQ3_XXSqwen-3-5/2b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-2B-GGUF:BF16qwen-3-5/2b · BF16 · ollama · quantizer hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:IQ2_XXSqwen-3-5/35b-a3b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:IQ2_Mqwen-3-5/35b-a3b · IQ2_M · ollama · quantizer hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:IQ3_XXSqwen-3-5/35b-a3b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_Sqwen-3-5/35b-a3b · Q4_K_S · ollama · quantizer hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_Mqwen-3-5/35b-a3b · Q4_K_M · ollama · quantizer hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q8_0qwen-3-5/35b-a3b · Q8_0 · ollama · quantizer unsloth/Qwen3.5-35B-A3B-GGUF:BF16qwen-3-5/35b-a3b · BF16 · llamacpp · quantizer hf.co/unsloth/Qwen3.5-4B-GGUF:IQ2_XXSqwen-3-5/4b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-4B-GGUF:IQ2_Mqwen-3-5/4b · IQ2_M · ollama · quantizer hf.co/unsloth/Qwen3.5-4B-GGUF:IQ3_XXSqwen-3-5/4b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_0qwen-3-5/4b · Q4_0 · ollama · quantizer hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_Mqwen-3-5/4b · Q4_K_M · ollama · quantizer hf.co/unsloth/Qwen3.5-4B-GGUF:Q8_0qwen-3-5/4b · Q8_0 · ollama · quantizer hf.co/unsloth/Qwen3.5-4B-GGUF:BF16qwen-3-5/4b · BF16 · ollama · quantizer hf.co/unsloth/Qwen3.5-9B-GGUF:IQ2_XXSqwen-3-5/9b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-9B-GGUF:IQ2_Mqwen-3-5/9b · IQ2_M · ollama · quantizer hf.co/unsloth/Qwen3.5-9B-GGUF:IQ3_XXSqwen-3-5/9b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_0qwen-3-5/9b · Q4_0 · ollama · quantizer hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_Mqwen-3-5/9b · Q4_K_M · ollama · quantizer hf.co/unsloth/Qwen3.5-9B-GGUF:Q8_0qwen-3-5/9b · Q8_0 · ollama · quantizer hf.co/unsloth/Qwen3.5-9B-GGUF:BF16qwen-3-5/9b · BF16 · ollama · quantizer hf.co/unsloth/Qwen3.6-27B-GGUF:IQ2_XXSqwen-3-6/27b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.6-27B-GGUF:IQ2_Mqwen-3-6/27b · IQ2_M · ollama · quantizer hf.co/unsloth/Qwen3.6-27B-GGUF:IQ3_XXSqwen-3-6/27b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.6-27B-GGUF:Q4_0qwen-3-6/27b · Q4_0 · ollama · quantizer hf.co/unsloth/Qwen3.6-27B-GGUF:Q4_K_Mqwen-3-6/27b · Q4_K_M · ollama · quantizer hf.co/unsloth/Qwen3.6-27B-GGUF:Q8_0qwen-3-6/27b · Q8_0 · ollama · quantizer unsloth/Qwen3.6-27B-GGUF:BF16qwen-3-6/27b · BF16 · llamacpp · quantizer hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:IQ1_Mqwen-3-6/35b-a3b · IQ1_M · ollama · quantizer hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:IQ2_XXSqwen-3-6/35b-a3b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:IQ3_XXSqwen-3-6/35b-a3b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_Sqwen-3-6/35b-a3b · Q4_K_S · ollama · quantizer hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_Mqwen-3-6/35b-a3b · Q4_K_M · ollama · quantizer hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q8_0qwen-3-6/35b-a3b · Q8_0 · ollama · quantizer unsloth/Qwen3.6-35B-A3B-GGUF:BF16qwen-3-6/35b-a3b · BF16 · llamacpp · quantizer unsloth/Qwen3.6-35B-A3B-NVFP4-Fastqwen-3-6/35b-a3b~unsloth-fast · W4A4 · vllm · derivative hf.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF:IQ1_Mqwen-3-6/35b-a3b~unsloth-mtp · IQ1_M · ollama · derivative hf.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF:IQ2_XXSqwen-3-6/35b-a3b~unsloth-mtp · IQ2_XXS · ollama · derivative hf.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF:IQ3_XXSqwen-3-6/35b-a3b~unsloth-mtp · IQ3_XXS · ollama · derivative hf.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF:Q4_K_Sqwen-3-6/35b-a3b~unsloth-mtp · Q4_K_S · ollama · derivative hf.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF:Q4_K_Mqwen-3-6/35b-a3b~unsloth-mtp · Q4_K_M · ollama · derivative hf.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF:Q8_0qwen-3-6/35b-a3b~unsloth-mtp · Q8_0 · ollama · derivative unsloth/Qwen3.6-35B-A3B-MTP-GGUF:BF16qwen-3-6/35b-a3b~unsloth-mtp · BF16 · llamacpp · derivative hf.co/unsloth/Qwen3.8-27B-GGUF:IQ1_Sqwen-3-8/27b · IQ1_S · ollama · quantizer hf.co/unsloth/Qwen3.8-27B-GGUF:IQ2_XXSqwen-3-8/27b · IQ2_XXS · ollama · quantizer hf.co/unsloth/Qwen3.8-27B-GGUF:IQ3_XXSqwen-3-8/27b · IQ3_XXS · ollama · quantizer hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_Sqwen-3-8/27b · Q4_K_S · ollama · quantizer hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_Mqwen-3-8/27b · Q4_K_M · ollama · quantizer hf.co/unsloth/Qwen3.8-27B-GGUF:Q8_0qwen-3-8/27b · Q8_0 · ollama · quantizer unsloth/Qwen3.8-27B-GGUF:BF16qwen-3-8/27b · BF16 · llamacpp · quantizer unsloth/Qwen-Image-2.1qwen-image/2-1 · diffusers · quantizer unsloth/Qwen-Image-2.1-Turbo-FP8qwen-image/2-1-turbo · FP8 · diffusers · quantizer unsloth/Qwen-Imageqwen-image/base · diffusers · quantizer unsloth/SmolLM3-3Bsmollm-3/3b~unsloth · BF16 · vllm · derivative hf.co/unsloth/SmolLM3-3B-128K-GGUF:IQ2_XXSsmollm-3/3b~unsloth-128k · IQ2_XXS · ollama · derivative hf.co/unsloth/SmolLM3-3B-128K-GGUF:IQ2_Msmollm-3/3b~unsloth-128k · IQ2_M · ollama · derivative hf.co/unsloth/SmolLM3-3B-128K-GGUF:IQ3_XXSsmollm-3/3b~unsloth-128k · IQ3_XXS · ollama · derivative hf.co/unsloth/SmolLM3-3B-128K-GGUF:Q4_0smollm-3/3b~unsloth-128k · Q4_0 · ollama · derivative hf.co/unsloth/SmolLM3-3B-128K-GGUF:Q4_K_Msmollm-3/3b~unsloth-128k · Q4_K_M · ollama · derivative hf.co/unsloth/SmolLM3-3B-128K-GGUF:Q8_0smollm-3/3b~unsloth-128k · Q8_0 · ollama · derivative hf.co/unsloth/SmolLM3-3B-128K-GGUF:BF16smollm-3/3b~unsloth-128k · BF16 · ollama · derivative unsloth/Step-3.7-Flash-GGUF:IQ1_Mstep-3-7/flash · IQ1_M · llamacpp · quantizer unsloth/Step-3.7-Flash-GGUF:Q4_K_Mstep-3-7/flash · Q4_K_M · llamacpp · quantizer unsloth/Wan2.2-TI2V-5B-FP8wan-2-2/ti2v-5b · FP8 · diffusers · quantizer