Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
mlx-community
/
granite-4.0-h-tiny-5bit-MLX
like
2
Follow
MLX Community
7.85k
Text Generation
MLX
Safetensors
English
granitemoehybrid
ibm
granite
apple-silicon
mamba2
transformer
hybrid
Mixture of Experts
long-context
instruct
quantized
5bit
MoE
conversational
5-bit
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
granite-4.0-h-tiny-5bit-MLX
4.78 GB
1 contributor
History:
5 commits
Susant-Achary
Update README.md
d197c78
verified
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
README.md
3.68 kB
Update README.md
3 months ago
chat_template.jinja
6.1 kB
Add MLX 5-bit quantized weights
3 months ago
config.json
12 kB
Add MLX 5-bit quantized weights
3 months ago
generation_config.json
147 Bytes
Add MLX 5-bit quantized weights
3 months ago
merges.txt
917 kB
Add MLX 5-bit quantized weights
3 months ago
model.safetensors
4.77 GB
xet
Add MLX 5-bit quantized weights
3 months ago
model.safetensors.index.json
101 kB
Add MLX 5-bit quantized weights
3 months ago
special_tokens_map.json
579 Bytes
Add MLX 5-bit quantized weights
3 months ago
tokenizer.json
7.15 MB
Add MLX 5-bit quantized weights
3 months ago
tokenizer_config.json
17.7 kB
Add MLX 5-bit quantized weights
3 months ago
vocab.json
1.61 MB
Add MLX 5-bit quantized weights
3 months ago
