Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
majentik
/
gemma-4-26B-A4B-RotorQuant-MLX-2bit
like
0
Image-Text-to-Text
MLX
Safetensors
gemma4
rotorquant
kv-cache-quantization
gemma
multimodal
quantized
2bit
2-bit
arxiv:
2504.19874
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
gemma-4-26B-A4B-RotorQuant-MLX-2bit
9.23 GB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
majentik
Add MLX quantized model with KV cache compression
66b0d5e
verified
3 days ago
.gitattributes
Safe
1.57 kB
Add MLX quantized model with KV cache compression
3 days ago
README.md
4.62 kB
Add MLX quantized model with KV cache compression
3 days ago
config.json
27.9 kB
Add MLX quantized model with KV cache compression
3 days ago
generation_config.json
Safe
181 Bytes
Add MLX quantized model with KV cache compression
3 days ago
model-00001-of-00003.safetensors
2.94 GB
xet
Add MLX quantized model with KV cache compression
3 days ago
model-00002-of-00003.safetensors
2.95 GB
xet
Add MLX quantized model with KV cache compression
3 days ago
model-00003-of-00003.safetensors
3.31 GB
xet
Add MLX quantized model with KV cache compression
3 days ago
model.safetensors.index.json
Safe
177 kB
Add MLX quantized model with KV cache compression
3 days ago
processor_config.json
Safe
627 Bytes
Add MLX quantized model with KV cache compression
3 days ago
tokenizer.json
Safe
32.2 MB
xet
Add MLX quantized model with KV cache compression
3 days ago
tokenizer_config.json
Safe
1.5 kB
Add MLX quantized model with KV cache compression
3 days ago
