4-bit Open on Hugging Face
Parameters
6.7B
Weights (est.)
≈ 3.8 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-tiny-preview-4bit --prompt "Hello"
Details
- Base model
- ibm-granite/granite-4.0-tiny-preview (quantized)
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 90 in the last 30 days · 770 all time · 0 likes
- Published
- 2025-09-10 · updated 2025-09-10 (1y ago)
- Tags
- granitemoehybrid, language, granite-4.0
Other MLX builds of ibm-granite/granite-4.0-tiny-preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-4.0-tiny-preview-4bit (this one) | 4-bit | ≈ 3.8 GB | 8 GB+ | 90 |
| granite-4.0-tiny-preview-8bit | 8-bit | ≈ 7.1 GB | 16 GB+ | 38 |