Formats

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

#ModelGGUF
1Llama-3.1-8B-InstructMeta Llama489
2Qwen3-0.6BQwen331
3Llama-3.2-1B-InstructMeta Llama251
4gemma-2-2b-itGoogle153
5gemma-2-9b-itGoogle125
6DeepSeek-R1-Distill-Qwen-32BDeepSeek80
7Qwen2.5-32B-InstructQwen68
8Phi-3-mini-128k-instructMicrosoft51
9Llama-3.3-70B-InstructMeta Llama45
10gemma-2-27b-itGoogle43
11aya-expanse-8bCohere Labs41
12QwQ-32B-PreviewQwen36
13Mistral-Small-3.1-24B-Instruct-2503Mistral AI33
14Nanbeige4.3-33BNanbeige33
15granite-3.1-2b-instructIBM Granite26
16Qwen2.5-72B-InstructQwen22
17granite-3.0-8b-instructIBM Granite21
18granite-3.1-8b-instructIBM Granite20
19Phi-3-medium-4k-instructMicrosoft18
20aya-expanse-32bCohere Labs16
21granite-3.0-2b-instructIBM Granite16
22DeepSeek-V3.1DeepSeek9
23Olmo-3.1-32B-InstructAi28
24Olmo-3.1-32B-ThinkAi27
25Hemmingway-1.5HemmingwayAI6
26Llama-3.1-Tulu-3-70BAi26
27Ling-flash-2.0inclusionAI5
28Ling-3.1-flash-1019inclusionAI5
29DeepSeek-V2.5-1210DeepSeek5
30INTELLECT-3Prime Intellect1