8-bit Open on Hugging Face
Parameters
32B
Weights (est.)
≈ 34.2 GB
Mac memory (est.)
48 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-small-8bit --prompt "Hello"
Details
- Base model
- ibm-granite/granite-4.0-h-small (quantized) · granite 4.0 h small on the radar →
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 41 in the last 30 days · 607 all time · 0 likes
- Published
- 2025-10-02 · updated 2025-10-02 (1y ago)
- Tags
- granitemoehybrid, language, granite-4.0
Other MLX builds of ibm-granite/granite-4.0-h-small
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-4.0-h-small-4bit | 4-bit | ≈ 18.1 GB | 24 GB+ | 95 |
| granite-4.0-h-small-8bit (this one) | 8-bit | ≈ 34.2 GB | 48 GB+ | 41 |