mlx-community/gpt-oss-120b-MXFP4-Q8

Quantization vs openai/gpt-oss-120b. mlx-community/gpt-oss-120b-MXFP4-Q8 is a quantized version of the other (U32/U8).

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse