Formats

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

#ModelAWQ
1Qwen3.8-27BQwen52
2Qwen3-8BQwen29
3Qwen3-14BQwen16
4Llama-3.1-8B-InstructMeta Llama16
5Qwen3-32BQwen16
6Qwen2.5-7B-InstructQwen15
7Llama-3.1-8BMeta Llama13
8Qwen3.5-27BQwen12
9Llama-3.3-70B-InstructMeta Llama12
10Qwen3-1.7BQwen11
11Llama-3.2-3B-InstructMeta Llama11
12Qwen3.5-35B-A3BQwen10
13Llama-3.2-1B-InstructMeta Llama10
14DeepSeek-R1-Distill-Qwen-32BDeepSeek10
15gemma-4-26B-A4B-itGoogle9
16Qwen2.5-1.5B-InstructQwen9
17Qwen2.5-0.5B-InstructQwen8
18Qwen3-4BQwen8
19Mistral-7B-Instruct-v0.2Mistral AI8
20phi-4Microsoft8
21gemma-2-9b-itGoogle8
22gemma-4-31B-itGoogle7
23Qwen3-4B-Instruct-2507Qwen7
24MiniMax-M2.5MiniMax7
25Qwen2.5-32B-InstructQwen7
26Llama-3.2-1BMeta Llama7
27Mistral-7B-v0.1Mistral AI7
28Meta-Llama-3-8BMeta Llama7
29Qwen3-30B-A3BQwen6
30QwQ-32BQwen6
31Qwen3-Coder-30B-A3B-InstructQwen5
32Qwen2.5-3B-InstructQwen5
33Qwen2.5-Coder-7B-InstructQwen5
34pythia-70m-dedupedEleutherAI5
35Meta-Llama-3-8B-InstructMeta Llama5
36Llama-2-7b-hfMeta Llama5
37Qwen2.5-72B-InstructQwen5
38Qwen3-0.6BQwen4
39pythia-160mEleutherAI4
40DeepSeek-R1DeepSeek4
41gemma-3-4b-itGoogle4
42Qwen2.5-Coder-32B-InstructQwen4
43DeepSeek-R1-Distill-Qwen-1.5BDeepSeek4
44Qwen3-Coder-NextQwen4
45Llama-3.2-3BMeta Llama4
46gemma-3-27b-itGoogle4
47Llama-2-7b-chat-hfMeta Llama4
48Mistral-Small-24B-Instruct-2501Mistral AI4
49Qwen3-235B-A22B-Instruct-2507Qwen4
50MiniMax-M2.1MiniMax4
51Qwen3.5-2BQwen3
52Qwen2.5-Coder-14B-InstructQwen3
53DeepSeek-V3DeepSeek3
54GLM-5Z.ai3
55TinyLlama-1.1B-Chat-v1.0TinyLlama3
56Qwen3.5-122B-A10BQwen3
57Mixtral-8x7B-Instruct-v0.1Mistral AI3
58DeepSeek-V3.1DeepSeek3
59Phi-3.5-mini-instructMicrosoft3
60MiniMax-M2.7MiniMax3
61DeepSeek-R1-0528DeepSeek3
62MiMo-V2.5Xiaomi MiMo3
63DeepSeek-V3.2-ExpDeepSeek3
64SOLAR-10.7B-Instruct-v1.0Upstage3
65Nanbeige4.3-33BNanbeige3
66QwQ-32B-PreviewQwen3
67Llama-2-70b-chat-hfMeta Llama3
68SmolLM2-135MHugging Face2
69NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA2
70GLM-4.7-FlashZ.ai2
71MiniCPM5-2BOpenBMB2
72Qwen3-30B-A3B-Instruct-2507Qwen2
73Qwen3.5-397B-A17BQwen2
74gemma-3-12b-itGoogle2
75Ornith-1.5-35B-A3BOrnith2
76Qwen3-VL-235B-A22B-InstructQwen2
77Phi-3-mini-128k-instructMicrosoft2
78gemma-3-1b-itGoogle2
79DeepSeek-V3-0324DeepSeek2
80Mistral-Small-3.1-24B-Instruct-2503Mistral AI2
81Llama-2-13b-chat-hfMeta Llama2
82Mistral-7B-Instruct-v0.1Mistral AI2
83MiniMax-M2MiniMax2
84Llama-3.1-70B-InstructMeta Llama2
85granite-4.1-8bIBM Granite2
86flintRecursiveSI2
87GLM-4.7Z.ai2
88granite-3.1-8b-instructIBM Granite2
89aya-expanse-8bCohere Labs2
90DeepSeek-V3.2DeepSeek1
91GLM-5.3-FlashZ.ai1
92DeepSeek-V4-Flash-0731DeepSeek1
93Ornith-1.0-35BOrnith1
94Qwen2.5-0.5BQwen1
95Ornith-1.0-9BOrnith1
96Laguna-XS.2Poolside1
97Phi-3-mini-4k-instructMicrosoft1
98Qwen3-235B-A22BQwen1
99MiniCPM5-1BOpenBMB1
100gemma-2-2b-itGoogle1