Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
baa-ai
/
Gemma-4-26B-A4B-it-RAM-14GB-MLX
like
6
Follow
baa.ai
41
MLX
Safetensors
gemma4
quantized
mixed-precision
Mixture of Experts
4-bit precision
License:
gemma
Model card
Files
Files and versions
xet
Community
Use this model
main
Gemma-4-26B-A4B-it-RAM-14GB-MLX
15.3 GB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
tomkay
Fix YAML metadata formatting
d4518d4
verified
7 days ago
.gitattributes
Safe
1.57 kB
RAM 14GB mixed-precision quantization of Gemma-4-26B-A4B-it
16 days ago
README.md
Safe
2.62 kB
Fix YAML metadata formatting
7 days ago
chat_template.jinja
Safe
12 kB
RAM 14GB mixed-precision quantization of Gemma-4-26B-A4B-it
16 days ago
config.json
Safe
76 kB
Reconvert with mlx_vlm: restore vision encoder weights
16 days ago
generation_config.json
Safe
208 Bytes
RAM 14GB mixed-precision quantization of Gemma-4-26B-A4B-it
16 days ago
model-00001-of-00003.safetensors
Safe
5.3 GB
xet
RAM 14GB mixed-precision quantization of Gemma-4-26B-A4B-it
16 days ago
model-00002-of-00003.safetensors
Safe
5.32 GB
xet
RAM 14GB mixed-precision quantization of Gemma-4-26B-A4B-it
16 days ago
model-00003-of-00003.safetensors
Safe
4.6 GB
xet
Reconvert with mlx_vlm: restore vision encoder weights
16 days ago
model.safetensors.index.json
Safe
168 kB
Reconvert with mlx_vlm: restore vision encoder weights
16 days ago
processor_config.json
Safe
902 Bytes
Reconvert with mlx_vlm: restore vision encoder weights
16 days ago
tokenizer.json
Safe
32.2 MB
xet
RAM 14GB mixed-precision quantization of Gemma-4-26B-A4B-it
16 days ago
tokenizer_config.json
Safe
2.69 kB
Reconvert with mlx_vlm: restore vision encoder weights
16 days ago
