4-bit Open on Hugging Face
Parameters
352M
Weights (est.)
≈ 198 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-4.0-350m-4bit --prompt "Hello"
Details
- Base model
- ibm-granite/granite-4.0-350m (quantized)
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 143 in the last 30 days · 469 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-4.0-350m
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-4.0-350m-3bit | 3-bit | ≈ 154 MB | 8 GB+ | 41 |
| granite-4.0-350m-4bit (this one) | 4-bit | ≈ 198 MB | 8 GB+ | 143 |
| granite-4.0-350m-5bit | 5-bit | ≈ 242 MB | 8 GB+ | 34 |
| granite-4.0-350m-6bit | 6-bit | ≈ 286 MB | 8 GB+ | 28 |
| granite-4.0-350m-8bit | 8-bit | ≈ 374 MB | 8 GB+ | 55 |
| granite-4.0-350m-bf16 | bf16 | ≈ 705 MB | 8 GB+ | 28 |