mlx-community/gemma-3n-E2B-it-lm-4bit

Quantization vs google/gemma-3n-E2B-it. mlx-community/gemma-3n-E2B-it-lm-4bit 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