majentik
/

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

Image-Text-to-Text

kv-cache-quantization

4-bit precision

Model card Files Files and versions

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

Commit History

Add MLX 4-bit quantized Gemma 4 31B

79a981b
verified

majentik commited on 2 days ago

initial commit

77e1405
verified

majentik commited on 2 days ago