Formats

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

#ModelMLX
1Qwen3.8-27BQwen485
2gemma-4-26B-A4B-itGoogle88
3Ornith-1.5-35B-A3BOrnith88
4Ornith-1.0-35BOrnith85
5gemma-4-31B-itGoogle65
6gpt-oss-20bOpenAI64
7Qwen3.5-35B-A3BQwen62
8Qwen3.5-2BQwen56
9Qwen3.5-122B-A10BQwen54
10Qwen3-Coder-NextQwen53
11Muse-Glimmer-30Bmeta-models53
12NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA51
13Qwen3-0.6BQwen50
14flintRecursiveSI50
15Qwen3.5-27BQwen48
16Qwen2.5-7B-InstructQwen47
17GLM-5.3-FlashZ.ai45
18Ornith-1.0-9BOrnith43
19gpt-oss-120bOpenAI41
20granite-4.1-8bIBM Granite41
21Qwen3-1.7BQwen40
22Qwen3-4B-Instruct-2507Qwen40
23Qwen3-8BQwen39
24MiniMax-M2.7MiniMax39
25Qwen2.5-3B-InstructQwen37
26LFM3-1.7BLiquid AI37
27MiniCPM5-2BOpenBMB35
28Qwen2.5-1.5B-InstructQwen31
29Qwen2.5-0.5B-InstructQwen31
30Qwen3-Coder-30B-A3B-InstructQwen31
31Qwen2.5-Coder-7B-InstructQwen31
32granite-4.2-8bIBM Granite31
33QwQ-32B-PreviewQwen31
34Qwen3-4BQwen30
35GLM-4.7-FlashZ.ai30
36granite-4.2-3bIBM Granite30
37LFM2.5-24B-A2BLiquid AI30
38Nanbeige4.3-33BNanbeige30
39DeepSeek-V4-Flash-0731DeepSeek29
40QwQ-32BQwen29
41gemma-3-1b-itGoogle27
42DeepSeek-V4-FlashDeepSeek26
43Hy3Tencent26
44Ornith-1.5-122BOrnith26
45Mistral-Small-3.2-24B-Instruct-2506Mistral AI25
46Qwen3-30B-A3B-Instruct-2507Qwen23
47Qwen3.5-397B-A17BQwen23
48Qwen2.5-Coder-32B-InstructQwen23
49MiniCPM5-1BOpenBMB23
50GLM-5.2Z.ai22
51Qwen2.5-Coder-14B-InstructQwen21
52NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA21
53Spark-X2.6-4BXHToken21
54Qwen3-Next-80B-A3B-InstructQwen19
55InklingThinking Machines18
56GLM-4.5-AirZ.ai18
57gemma-2-2b-itGoogle18
58Qwen3-235B-A22B-Instruct-2507Qwen18
59granite-4.2-30bIBM Granite18
60Qwen3-14BQwen17
61DeepSeek-R1-Distill-Qwen-1.5BDeepSeek17
62Qwen3-30B-A3BQwen16
63DeepSeek-R1-Distill-Qwen-32BDeepSeek16
64gemma-3-4b-itGoogle15
65Qwen3-32BQwen14
66GLM-5.3Z.ai14
67DeepSeek-V4.1-FlashDeepSeek14
68TinyLlama-1.1B-Chat-v1.0TinyLlama14
69Llama-3.2-3B-InstructMeta Llama14
70gemma-3n-E4B-itGoogle14
71phi-4Microsoft13
72Qwen3-Next-80B-A3B-ThinkingQwen13
73Qwen3-235B-A22B-Thinking-2507Qwen13
74Llama-3.1-8B-InstructMeta Llama12
75NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA12
76NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA12
77Qwen2.5-0.5BQwen12
78MiniMax-M2.5MiniMax12
79Phi-3.5-mini-instructMicrosoft12
80Ling-3.0-tinyinclusionAI12
81Llama-3.2-1B-InstructMeta Llama11
82Inkling-SmallThinking Machines11
83MiniMax-M3MiniMax11
84Olmo-3-32B-ThinkAi211
85Nanbeige4.1-3BNanbeige11
86Spark-X2.5-4BXHToken11
87granite-4.0-h-smallIBM Granite10
88Sage-A1.5InternScience10
89Kimi-K3Moonshot AI9
90Laguna-XS.2Poolside9
91Qwen2.5-32B-InstructQwen9
92Mistral-7B-v0.1Mistral AI9
93Llama-3.3-70B-InstructMeta Llama9
94Mistral-Small-24B-Instruct-2501Mistral AI9
95Hemmingway-1.5HemmingwayAI9
96GLM-5.1Z.ai8
97Laguna-M.1Poolside8
98Llama-3.2-3BMeta Llama8
99Qwen3-235B-A22BQwen8
100gemma-2-9b-itGoogle8