roman220220/gemma-4-26B-A4B-it-assistant-mlx-8bit

Quantization vs google/gemma-4-26B-A4B-it-assistant. roman220220/gemma-4-26B-A4B-it-assistant-mlx-8bit 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