Formats

Quantized builds on Hugging Face by file format, counted Nov 18, 2026.

#ModelGGUF
1Qwen3.8-27BQwen793
2Llama-3.1-8B-InstructMeta Llama489
3Llama-3.2-3B-InstructMeta Llama393
4Qwen3-0.6BQwen331
5Qwen2.5-7B-InstructQwen276
6Qwen3-8BQwen268
7Qwen3-1.7BQwen258
8Llama-3.2-1B-InstructMeta Llama251
9Qwen2.5-3B-InstructQwen250
10Qwen3-4B-Instruct-2507Qwen241
11Qwen2.5-1.5B-InstructQwen239
12Qwen2.5-0.5B-InstructQwen239
13gemma-4-26B-A4B-itGoogle216
14Llama-3.1-8BMeta Llama216
15Qwen3-4BQwen207
16Qwen2.5-Coder-7B-InstructQwen207
17DeepSeek-R1-Distill-Qwen-1.5BDeepSeek197
18Qwen3.5-2BQwen189
19gemma-3-4b-itGoogle181
20gemma-3-1b-itGoogle179
21Qwen3.5-35B-A3BQwen176
22Llama-3.2-1BMeta Llama166
23Meta-Llama-3-8B-InstructMeta Llama164
24Meta-Llama-3-8BMeta Llama163
25gemma-2-2b-itGoogle153
26gemma-4-31B-itGoogle152
27Phi-3-mini-4k-instructMicrosoft137
28Phi-3.5-mini-instructMicrosoft134
29gemma-2-9b-itGoogle125
30Qwen3-14BQwen118
31gemma-3-12b-itGoogle113
32phi-4Microsoft103
33gpt-oss-20bOpenAI101
34DeepSeek-V4-Flash-0731DeepSeek100
35Qwen3-Coder-30B-A3B-InstructQwen99
36TinyLlama-1.1B-Chat-v1.0TinyLlama99
37Llama-3.2-3BMeta Llama95
38Qwen3.5-27BQwen94
39gemma-3-27b-itGoogle92
40Qwen2.5-Coder-14B-InstructQwen88
41LFM3-1.7BLiquid AI87
42GLM-5.3-FlashZ.ai86
43Ornith-1.5-35B-A3BOrnith86
44Mistral-7B-v0.1Mistral AI83
45DeepSeek-R1-Distill-Qwen-32BDeepSeek80
46Mistral-7B-Instruct-v0.2Mistral AI74
47Muse-Glimmer-30Bmeta-models72
48Qwen2.5-Coder-32B-InstructQwen71
49Qwen3.5-122B-A10BQwen70
50Qwen2.5-32B-InstructQwen68
51Qwen2.5-0.5BQwen67
52DeepSeek-V4-FlashDeepSeek65
53QwQ-32BQwen64
54MiniCPM5-1BOpenBMB60
55MiniCPM5-2BOpenBMB59
56Qwen3-30B-A3B-Instruct-2507Qwen59
57Llama-2-7b-chat-hfMeta Llama59
58Qwen3-32BQwen57
59Qwen3-30B-A3BQwen57
60Mistral-Small-24B-Instruct-2501Mistral AI55
61gemma-3n-E4B-itGoogle52
62GLM-4.7-FlashZ.ai51
63Phi-3-mini-128k-instructMicrosoft51
64gpt-oss-120bOpenAI49
65gpt2OpenAI (community)48
66NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA47
67Llama-3.3-70B-InstructMeta Llama45
68GLM-5.2Z.ai43
69gemma-2-27b-itGoogle43
70aya-expanse-8bCohere Labs41
71flintRecursiveSI40
72NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA38
73LFM2.5-24B-A2BLiquid AI38
74Llama-3.1-70B-InstructMeta Llama37
75QwQ-32B-PreviewQwen36
76NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA35
77MiniMax-M2.7MiniMax35
78Spark-X2.5-4BXHToken34
79Mistral-Small-3.1-24B-Instruct-2503Mistral AI33
80Nanbeige4.3-33BNanbeige33
81Nanbeige4.1-3BNanbeige33
82SmolLM2-135MHugging Face32
83phi-2Microsoft32
84Spark-X2.6-4BXHToken32
85Llama-2-7b-hfMeta Llama30
86granite-4.1-8bIBM Granite30
87Qwen3-Coder-NextQwen29
88granite-4.2-8bIBM Granite28
89Ling-3.0-tinyinclusionAI28
90gemma-2bGoogle27
91DeepSeek-R1DeepSeek26
92Qwen3-Next-80B-A3B-InstructQwen26
93Mistral-Small-3.2-24B-Instruct-2506Mistral AI26
94granite-4.2-3bIBM Granite26
95granite-3.1-2b-instructIBM Granite26
96NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA25
97Mixtral-8x7B-Instruct-v0.1Mistral AI25
98DeepSeek-V4.1-FlashDeepSeek24
99tiny-aya-globalCohere Labs24
100Sage-A1.5InternScience23