txgsync/gpt-oss-20b-Derestricted-mxfp4-mlx

Quantization vs ArliAI/gpt-oss-20b-Derestricted. txgsync/gpt-oss-20b-Derestricted-mxfp4-mlx is a quantized version of the other (U32/BF16).

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

On the Hub · Downloads on Model Pulse