Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
mlx-community
/
granite-4.0-h-tiny-3bit-MLX
like
2
Follow
MLX Community
7.57k
Text Generation
MLX
Safetensors
English
granitemoehybrid
ibm
granite
apple-silicon
mamba2
transformer
hybrid
Mixture of Experts
long-context
instruct
quantized
MoE
conversational
3-bit
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
granite-4.0-h-tiny-3bit-MLX
/
merges.txt
Susant-Achary
Add MLX 3-bit quantized weights
4c05c40
verified
2 months ago
raw
Copy download link
history
contribute
delete
Safe
917 kB
File too large to display, you can
check the raw version
instead.