Hugging Face's logo

majentik
/
gemma-4-26B-A4B-RotorQuant-MLX-8bit

Image-Text-to-Text
MLX
Safetensors
gemma4
rotorquant
kv-cache-quantization
gemma
multimodal
quantized
8bit
8-bit precision
Model card Files
xet
 Community
gemma-4-26B-A4B-RotorQuant-MLX-8bit / tokenizer.json

Commit History

Add MLX quantized model with KV cache compression
93b7258
verified

majentik commited on