Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
majentik
/
gemma-4-E2B-RotorQuant-MLX-8bit
like
0
Image-Text-to-Text
MLX
Safetensors
gemma4
rotorquant
kv-cache-quantization
gemma
multimodal
quantized
8bit
8-bit precision
arxiv:
2504.19874
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
gemma-4-E2B-RotorQuant-MLX-8bit
/
generation_config.json
Commit History
Add MLX quantized model with KV cache compression
ca1fe84
verified
majentik
commited on
3 days ago
majentik commited on 