Formats

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

#ModelGPTQ
1Qwen3.8-27BQwen120
2Llama-3.2-1B-InstructMeta Llama35
3Llama-3.1-8B-InstructMeta Llama31
4Qwen3-8BQwen30
5Llama-3.1-8BMeta Llama27
6Llama-3.2-3B-InstructMeta Llama26
7Qwen3-1.7BQwen19
8SmolLM2-135MHugging Face18
9Llama-3.2-1BMeta Llama18
10Llama-3.2-3BMeta Llama15
11Qwen2.5-1.5B-InstructQwen14
12Qwen3-0.6BQwen13
13Qwen3-32BQwen13
14Qwen3-Coder-30B-A3B-InstructQwen12
15Qwen3.5-35B-A3BQwen12
16Qwen3-30B-A3B-Instruct-2507Qwen12
17Muse-Glimmer-30Bmeta-models12
18Qwen3-4B-Instruct-2507Qwen11
19Meta-Llama-3-8B-InstructMeta Llama11
20Ornith-1.5-35B-A3BOrnith11
21Qwen2.5-72B-InstructQwen11
22Qwen3-4BQwen10
23pythia-160mEleutherAI10
24phi-4Microsoft10
25Qwen3-14BQwen9
26DeepSeek-R1-Distill-Qwen-32BDeepSeek9
27Mistral-Small-24B-Instruct-2501Mistral AI9
28LFM2.5-24B-A2BLiquid AI9
29Qwen2.5-7B-InstructQwen8
30pythia-70m-dedupedEleutherAI8
31Llama-2-7b-chat-hfMeta Llama8
32gemma-4-31B-itGoogle7
33Qwen2.5-0.5B-InstructQwen7
34Qwen2.5-3B-InstructQwen7
35Qwen3.5-27BQwen7
36gemma-2-9b-itGoogle7
37Meta-Llama-3-8BMeta Llama7
38QwQ-32BQwen7
39gemma-4-26B-A4B-itGoogle6
40Qwen2.5-Coder-32B-InstructQwen6
41Mistral-7B-v0.1Mistral AI6
42flintRecursiveSI6
43Qwen3.5-2BQwen5
44Nanbeige4.3-33BNanbeige5
45QwQ-32B-PreviewQwen5
46Qwen3-30B-A3BQwen4
47Hy3Tencent4
48NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA4
49TinyLlama-1.1B-Chat-v1.0TinyLlama4
50DeepSeek-R1-Distill-Qwen-1.5BDeepSeek4
51Mixtral-8x7B-Instruct-v0.1Mistral AI4
52Qwen3-235B-A22BQwen4
53Phi-3.5-mini-instructMicrosoft4
54Llama-2-7b-hfMeta Llama4
55DeepSeek-R1-0528DeepSeek4
56LFM3-1.7BLiquid AI4
57DeepSeek-R1DeepSeek3
58Qwen2.5-Coder-14B-InstructQwen3
59GLM-4.5-AirZ.ai3
60Mistral-7B-Instruct-v0.2Mistral AI3
61gemma-3-4b-itGoogle3
62MiniCPM5-2BOpenBMB3
63Qwen3.5-122B-A10BQwen3
64Qwen2.5-32B-InstructQwen3
65Llama-3.3-70B-InstructMeta Llama3
66gemma-3-27b-itGoogle3
67phi-2Microsoft3
68Llama-2-13b-chat-hfMeta Llama3
69SOLAR-10.7B-Instruct-v1.0Upstage3
70GLM-4.6Z.ai3
71Qwen2-72B-InstructQwen3
72Llama-2-70b-chat-hfMeta Llama3
73GLM-5.3-FlashZ.ai2
74DeepSeek-V4-Flash-0731DeepSeek2
75GLM-5.3Z.ai2
76DeepSeek-V4.1-FlashDeepSeek2
77Qwen2.5-Coder-7B-InstructQwen2
78DeepSeek-V3DeepSeek2
79DeepSeek-V4-FlashDeepSeek2
80Qwen3.5-397B-A17BQwen2
81Ornith-1.5-122BOrnith2
82Qwen3-Coder-NextQwen2
83GLM-5.2Z.ai2
84gemma-2-2b-itGoogle2
85MiniMax-M3MiniMax2
86MiniMax-M2MiniMax2
87Llama-3.1-70B-InstructMeta Llama2
88GLM-4.7Z.ai2
89Meta-Llama-3-70B-InstructMeta Llama2
90granite-4.2-3bIBM Granite2
91Spark-X2.6-4BXHToken2
92Spark-X2.5-4BXHToken2
93deepseek-llm-67b-chatDeepSeek2
94openchat_3.5openchat2
95gpt2OpenAI (community)1
96gpt-oss-20bOpenAI1
97gpt-oss-120bOpenAI1
98NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA1
99Ornith-1.0-35BOrnith1
100NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1