majentik
/

gemma-4-31B-RotorQuant-MLX-8bit

Image-Text-to-Text

kv-cache-quantization

8-bit precision

Model card Files Files and versions

gemma-4-31B-RotorQuant-MLX-8bit

Commit History

Add MLX 8-bit quantized Gemma 4 31B

c76c1be
verified

majentik commited on 2 days ago

initial commit

e8b283f
verified

majentik commited on 2 days ago