Most built on

Open models ranked by how many quantizations on Hugging Face name them as their base. Counted Nov 18, 2026.

#ModelQuantizations
1Qwen3.8-27BQwen1,854
2Llama-3.1-8B-InstructMeta Llama967
3Qwen3-0.6BQwen562
4Llama-3.2-3B-InstructMeta Llama560
5Qwen3-8BQwen522
6Qwen3-1.7BQwen518
7gemma-3-1b-itGoogle501
8gemma-3-4b-itGoogle494
9Qwen2.5-7B-InstructQwen454
10gemma-4-26B-A4B-itGoogle441
11Llama-3.2-1B-InstructMeta Llama438
12Qwen2.5-0.5B-InstructQwen395
13Qwen3-4BQwen388
14Qwen3-4B-Instruct-2507Qwen385
15Qwen2.5-1.5B-InstructQwen383
16gemma-4-31B-itGoogle367
17Llama-3.1-8BMeta Llama348
18Qwen2.5-3B-InstructQwen342
19Qwen3.5-2BQwen334
20Qwen3.5-35B-A3BQwen320
21Meta-Llama-3-8BMeta Llama285
22Qwen2.5-Coder-7B-InstructQwen283
23Meta-Llama-3-8B-InstructMeta Llama283
24DeepSeek-R1-Distill-Qwen-1.5BDeepSeek282
25gpt-oss-20bOpenAI265
26Llama-3.2-1BMeta Llama264
27Qwen3.5-27BQwen248
28GLM-5.3-FlashZ.ai245
29Qwen3-14BQwen229
30Ornith-1.5-35B-A3BOrnith222
31gemma-2-2b-itGoogle211
32DeepSeek-V4-Flash-0731DeepSeek205
33Phi-3.5-mini-instructMicrosoft204
34Muse-Glimmer-30Bmeta-models203
35Mistral-7B-v0.1Mistral AI196
36Qwen3-32BQwen190
37Qwen3-Coder-30B-A3B-InstructQwen186
38Phi-3-mini-4k-instructMicrosoft185
39gemma-2-9b-itGoogle183
40Qwen3.5-122B-A10BQwen179
41phi-4Microsoft175
42Llama-3.3-70B-InstructMeta Llama173
43Ornith-1.0-35BOrnith170
44TinyLlama-1.1B-Chat-v1.0TinyLlama168
45QwQ-32BQwen167
46gemma-3-12b-itGoogle163
47LFM3-1.7BLiquid AI162
48Qwen2.5-32B-InstructQwen159
49Llama-3.2-3BMeta Llama159
50Qwen3-30B-A3BQwen155
51GLM-5.2Z.ai149
52Qwen3-30B-A3B-Instruct-2507Qwen148
53DeepSeek-R1-Distill-Qwen-32BDeepSeek148
54gemma-3-27b-itGoogle147
55DeepSeek-V4.1-FlashDeepSeek141
56Qwen2.5-Coder-32B-InstructQwen141
57MiniCPM5-2BOpenBMB139
58Qwen2.5-Coder-14B-InstructQwen138
59gpt-oss-120bOpenAI137
60DeepSeek-V4-FlashDeepSeek137
61Llama-3.1-70B-InstructMeta Llama132
62NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA129
63GLM-5.3Z.ai120
64Qwen3-Coder-NextQwen120
65Qwen2.5-0.5BQwen118
66GLM-4.7-FlashZ.ai115
67Mistral-7B-Instruct-v0.2Mistral AI113
68MiniMax-M2.7MiniMax113
69flintRecursiveSI113
70Mistral-Small-24B-Instruct-2501Mistral AI109
71MiniCPM5-1BOpenBMB107
72Nanbeige4.3-33BNanbeige105
73QwQ-32B-PreviewQwen105
74Llama-2-7b-chat-hfMeta Llama104
75Ornith-1.0-9BOrnith101
76gpt2OpenAI (community)100
77Qwen2.5-72B-InstructQwen97
78LFM2.5-24B-A2BLiquid AI91
79Phi-3-mini-128k-instructMicrosoft87
80granite-4.1-8bIBM Granite84
81Qwen3.5-397B-A17BQwen81
82Qwen3-Next-80B-A3B-InstructQwen81
83SmolLM2-135MHugging Face80
84NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA80
85Llama-2-7b-hfMeta Llama78
86Qwen3-235B-A22B-Instruct-2507Qwen74
87gemma-3n-E4B-itGoogle74
88Mistral-Small-3.2-24B-Instruct-2506Mistral AI71
89DeepSeek-R1DeepSeek70
90Spark-X2.6-4BXHToken70
91granite-4.2-3bIBM Granite69
92GLM-4.5-AirZ.ai66
93Hy3Tencent66
94granite-4.2-8bIBM Granite66
95MiniMax-M2.5MiniMax64
96phi-2Microsoft64
97Mistral-Small-3.1-24B-Instruct-2503Mistral AI63
98Nanbeige4.1-3BNanbeige62
99NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA60
100gemma-2-27b-itGoogle60