Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
baa-ai
/
Gemma-4-31B-it-RAM-3bit-MLX
like
1
Follow
baa.ai
32
Image-Text-to-Text
MLX
Safetensors
gemma4
quantized
multimodal
conversational
4-bit precision
License:
gemma
Model card
Files
Files and versions
xet
Community
Use this model
main
Gemma-4-31B-it-RAM-3bit-MLX
19.5 GB
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
tomkay
Fix YAML metadata formatting
a9a60a2
verified
2 days ago
.gitattributes
Safe
1.57 kB
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
README.md
Safe
3.9 kB
Fix YAML metadata formatting
2 days ago
chat_template.jinja
Safe
16.4 kB
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
config.json
Safe
149 kB
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
generation_config.json
Safe
208 Bytes
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
model-00001-of-00004.safetensors
Safe
5.34 GB
xet
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
model-00002-of-00004.safetensors
Safe
5.36 GB
xet
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
model-00003-of-00004.safetensors
Safe
5.29 GB
xet
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
model-00004-of-00004.safetensors
Safe
3.5 GB
xet
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
model.safetensors.index.json
Safe
240 kB
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
processor_config.json
Safe
902 Bytes
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
tokenizer.json
Safe
32.2 MB
xet
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago
tokenizer_config.json
Safe
2.69 kB
Initial upload: Gemma 4 31B RAM 3bit with benchmark table
7 days ago