tokimoa/GPT-OSS-Swallow-20B-RL-v0.1-MLX-MXFP4

Quantization vs tokyotech-llm/GPT-OSS-Swallow-20B-RL-v0.1. tokimoa/GPT-OSS-Swallow-20B-RL-v0.1-MLX-MXFP4 is a quantized version of the other (U32/U8).

On the Hub · Downloads on Model Pulse