majentik
/

gemma-4-26B-A4B-it-RotorQuant-MLX-8bit

Image-Text-to-Text

kv-cache-quantization

8-bit precision

Model card Files Files and versions

gemma-4-26B-A4B-it-RotorQuant-MLX-8bit

28 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

majentik's picture

Add MLX quantized model with KV cache compression

01251c6 verified 4 days ago

.gitattributes

1.57 kB
Add MLX quantized model with KV cache compression 4 days ago
README.md

4.25 kB
Add MLX quantized model with KV cache compression 4 days ago
chat_template.jinja

12 kB
Add MLX quantized model with KV cache compression 4 days ago
config.json

33.4 kB
Add MLX quantized model with KV cache compression 4 days ago
generation_config.json

208 Bytes
Add MLX quantized model with KV cache compression 4 days ago
model-00001-of-00006.safetensors

5.18 GB
xet

Add MLX quantized model with KV cache compression 4 days ago
model-00002-of-00006.safetensors

5.21 GB
xet

Add MLX quantized model with KV cache compression 4 days ago
model-00003-of-00006.safetensors

5.21 GB
xet

Add MLX quantized model with KV cache compression 4 days ago
model-00004-of-00006.safetensors

5.21 GB
xet

Add MLX quantized model with KV cache compression 4 days ago
model-00005-of-00006.safetensors

5.21 GB
xet

Add MLX quantized model with KV cache compression 4 days ago
model-00006-of-00006.safetensors

1.95 GB
xet

Add MLX quantized model with KV cache compression 4 days ago
model.safetensors.index.json

177 kB
Add MLX quantized model with KV cache compression 4 days ago
processor_config.json

627 Bytes
Add MLX quantized model with KV cache compression 4 days ago
tokenizer.json

32.2 MB
xet

Add MLX quantized model with KV cache compression 4 days ago
tokenizer_config.json

2.69 kB
Add MLX quantized model with KV cache compression 4 days ago