4-bit Open on Hugging Face
Parameters
1.5B
Weights (est.)
≈ 823 MB
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-1b-base-4bit --prompt "Hello"
Details
- Base model
- ibm-granite/granite-4.0-h-1b-base (quantized)
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 31 in the last 30 days · 197 all time · 0 likes
- Published
- 2025-10-28 · updated 2025-10-28 (1y ago)
- Tags
- granitemoehybrid, language, granite-4.0
Other MLX builds of ibm-granite/granite-4.0-h-1b-base
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-4.0-h-1b-base-3bit | 3-bit | ≈ 641 MB | 8 GB+ | 27 |
| granite-4.0-h-1b-base-4bit (this one) | 4-bit | ≈ 823 MB | 8 GB+ | 31 |
| granite-4.0-h-1b-base-5bit | 5-bit | ≈ 1.0 GB | 8 GB+ | 23 |
| granite-4.0-h-1b-base-6bit | 6-bit | ≈ 1.2 GB | 8 GB+ | 21 |
| granite-4.0-h-1b-base-8bit | 8-bit | ≈ 1.6 GB | 8 GB+ | 28 |
| granite-4.0-h-1b-base-bf16 | bf16 | ≈ 2.9 GB | 8 GB+ | 22 |