lmstudio-community/gpt-oss-120b-MLX-8bit

Quantization vs openai/gpt-oss-120b. lmstudio-community/gpt-oss-120b-MLX-8bit is a quantized version of the other (U32/BF16).

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

On the Hub · Downloads on Model Pulse