majentik
/

gemma-4-26B-A4B-RotorQuant-MLX-2bit

Image-Text-to-Text

kv-cache-quantization

Model card Files Files and versions

gemma-4-26B-A4B-RotorQuant-MLX-2bit

Commit History

Add MLX quantized model with KV cache compression

66b0d5e
verified

majentik commited on 4 days ago

initial commit

322dced
verified

majentik commited on 4 days ago