4-bit Open on Hugging Face
Parameters
3.2B
Weights (est.)
≈ 1.8 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/granite-4.0-h-micro-4bit --prompt "Hello"
Details
- Base model
- ibm-granite/granite-4.0-h-micro (quantized)
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 1.1K in the last 30 days · 15K all time · 1 likes
- Published
- 2025-10-04 · updated 2025-10-04 (1y ago)
- Tags
- granitemoehybrid, language, granite-4.0
Other MLX builds of ibm-granite/granite-4.0-h-micro
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-4.0-h-micro-4bit (this one) | 4-bit | ≈ 1.8 GB | 8 GB+ | 1.1K |
| granite-4.0-h-micro-6bit | 6-bit | ≈ 2.6 GB | 8 GB+ | 38 |
| granite-4.0-h-micro-8bit | 8-bit | ≈ 3.4 GB | 8 GB+ | 70 |
| granite-4.0-h-tiny-4bit | 4-bit | ≈ 3.9 GB | 8 GB+ | 1.1K |