Quantized language models
Language models distributed in quantized or compressed formats, including GGUF
Where it stands
Open models1348 products1.16× its peers
Fastest products
1mzbac/voxtral-mini-3b-4bit-mixed · Open models67×
2mradermacher/zeta-2.1-GGUF · Open models50×
3peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF · Open models32×
4casperhansen/deepseek-r1-distill-llama-8b-awq · Open models31×
5turboderp/Qwen3.8-27B-exl3 · Open models26×
6zerofata/G4-MeroMero-31B-gguf · Open models20×
7mradermacher/Qwen3.8-14B-Instruct-Turbo-GGUF · Open models19×
8SicariusSicariiStuff/Impish_LLAMA_4B_GGUF · Open models18×
9tencent/Hy-MT2-1.8B-FP8 · Open models18×
10jeffcookio/gemma-3-12b-it-abliterated-gptqmodel-4b-128g · Open models17×
11casperhansen/mistral-small-24b-instruct-2501-awq · Open models17×
12bartowski/Qwen_Qwen3-4B-GGUF · Open models17×
13samuelchristlie/Ornith-1.0-9B-gguf · Open models16×
14mradermacher/Huihui-Qwen3.6-35B-A3B-abliterated-GGUF · Open models16×
15LocalAI-io/Llama-3-Kimodo-GGML · Open models15×16nvidia/Qwen3-Next-80B-A3B-Instruct-NVFP4 · Open models15×17mradermacher/LING-3.0-FLASH-ABLITERATED-i1-GGUF · Open models14×
18bartowski/Qwen2.5-32B-Instruct-GGUF · Open models13×
19Firworks/gemma-4-26B-A4B-it-fp8 · Open models12×
20tencent/Hy-MT2-7B-GGUF · Open models11×
21Intel/gemma-4-31B-it-int4-AutoRound · Open models11×
22RedHatAI/Qwen3.5-9B-quantized.w8a8 · Open models11×23mradermacher/openNemo-9B-Claude-Opus-4.6-distill-i1-GGUF · Open models10×
24TheDrummer/Anubis-Mini-8B-v1-GGUF · Open models10×
25RadixArk/GLM-5.3-NVFP4 · Open models10×4,370 products carry this theme. “× its peers” is the theme's median growth against the place's median.