majentik
/

gemma-4-31B-RotorQuant-MLX-4bit

Image-Text-to-Text

kv-cache-quantization

4-bit precision

Model card Files Files and versions

gemma-4-31B-RotorQuant-MLX-4bit

18.4 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

majentik's picture

Add MLX 4-bit quantized Gemma 4 31B

79a981b verified 2 days ago

.gitattributes

1.57 kB
Add MLX 4-bit quantized Gemma 4 31B 2 days ago
README.md

4 kB
Add MLX 4-bit quantized Gemma 4 31B 2 days ago
config.json

5.13 kB
Add MLX 4-bit quantized Gemma 4 31B 2 days ago
generation_config.json

181 Bytes
Add MLX 4-bit quantized Gemma 4 31B 2 days ago
model-00001-of-00004.safetensors

5.37 GB
xet

Add MLX 4-bit quantized Gemma 4 31B 2 days ago
model-00002-of-00004.safetensors

5.36 GB
xet

Add MLX 4-bit quantized Gemma 4 31B 2 days ago
model-00003-of-00004.safetensors

5.37 GB
xet

Add MLX 4-bit quantized Gemma 4 31B 2 days ago
model-00004-of-00004.safetensors

2.32 GB
xet

Add MLX 4-bit quantized Gemma 4 31B 2 days ago
model.safetensors.index.json

205 kB
Add MLX 4-bit quantized Gemma 4 31B 2 days ago
processor_config.json

627 Bytes
Add MLX 4-bit quantized Gemma 4 31B 2 days ago
tokenizer.json

32.2 MB
xet

Add MLX 4-bit quantized Gemma 4 31B 2 days ago
tokenizer_config.json

1.5 kB
Add MLX 4-bit quantized Gemma 4 31B 2 days ago