4-bit Open on Hugging Face
Parameters
3.4B
Weights (est.)
≈ 1.9 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-4.1-3b-nvfp4 --prompt "Hello"
Details
- Base model
- ibm-granite/granite-4.1-3b (quantized)
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 42 in the last 30 days · 963 all time · 1 likes
- Published
- 2026-04-30 · updated 2026-04-30 (6mo ago)
- Tags
- granite, language, granite-4.1
Other MLX builds of ibm-granite/granite-4.1-3b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-4.1-3b-4bit | 4-bit | ≈ 1.9 GB | 8 GB+ | 1.2K |
| granite-4.1-3b-mxfp4 | MXFP4 | ≈ 1.9 GB | 8 GB+ | 146 |
| granite-4.1-3b-nvfp4 (this one) | 4-bit | ≈ 1.9 GB | 8 GB+ | 42 |
| granite-4.1-3b-5bit | 5-bit | ≈ 2.3 GB | 8 GB+ | 31 |
| granite-4.1-3b-6bit | 6-bit | ≈ 2.8 GB | 8 GB+ | 28 |
| granite-4.1-3b-8bit | 8-bit | ≈ 3.6 GB | 8 GB+ | 227 |
| granite-4.1-3b-mxfp8 | MXFP8 | ≈ 3.6 GB | 8 GB+ | 42 |
| granite-4.1-3b-bf16 | bf16 | ≈ 6.8 GB | 16 GB+ | 55 |