mlx-community/gpt-oss-20b-mxfp4-bf16

Quantization vs openai/gpt-oss-20b. mlx-community/gpt-oss-20b-mxfp4-bf16 is a quantized version of the other (U32/BF16).

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

On the Hub · Downloads on Model Pulse