gpt-oss GGUF models
750 GGUF models in the gpt-oss family, quantized by 310 uploaders. Sizes run from 4M to 197B parameters. The longest trained context is 224K tokens.
About the gpt-oss GGUF models
gpt-oss is represented on ggufmodels.com by 750 GGUF models, quantized by 310 uploaders on Hugging Face. The most downloaded are Gpt-Oss-20B, gpt-oss-20b and gpt-oss-120b. Parameter counts run from 4M to 197B, and the longest trained context window is 224K tokens.
A Q4_K_M file of a gpt-oss model is between 0.4 to 147.9 GB, which is the quant most people start with. Most files come from mradermacher (272), bartowski (7) and nguyenthilaitrieulong (6). The quants you will meet most often are Q4_K_M (384), Q5_K_M (319), Q3_K_M (311) and Q2_K (308), where the number is how many models offer that quant.
Frequently asked questions
Which gpt-oss GGUF should I download?
The most downloaded gpt-oss GGUF here is Gpt-Oss-20B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a gpt-oss model need?
Q4_K_M files of gpt-oss models on this site range from 0.4 to 147.9 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do gpt-oss GGUF files come from?
The most common quantizers here are mradermacher, bartowski and nguyenthilaitrieulong. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.