5-bit Open on Hugging Face
Parameters
8.4B
Weights (est.)
≈ 5.8 GB
Mac memory (est.)
16 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-4.1-8b-5bit --prompt "Hello"
Details
- Base model
- ibm-granite/granite-4.1-8b (quantized)
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 5-bit
- Licence
- apache-2.0
- Downloads
- 30 in the last 30 days · 414 all time · 0 likes
- Published
- 2026-05-03 · updated 2026-05-03 (6mo ago)
- Tags
- granite, language, granite-4.1
Other MLX builds of ibm-granite/granite-4.1-8b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-4.1-8b-4bit | 4-bit | ≈ 4.7 GB | 8 GB+ | 894 |
| granite-4.1-8b-nvfp4 | 4-bit | ≈ 4.7 GB | 8 GB+ | 44 |
| granite-4.1-8b-mxfp4 | MXFP4 | ≈ 4.7 GB | 8 GB+ | 33 |
| granite-4.1-8b-5bit (this one) | 5-bit | ≈ 5.8 GB | 16 GB+ | 30 |
| granite-4.1-8b-6bit | 6-bit | ≈ 6.8 GB | 16 GB+ | 40 |
| granite-4.1-8b-8bit | 8-bit | ≈ 8.9 GB | 16 GB+ | 549 |
| granite-4.1-8b-mxfp8 | MXFP8 | ≈ 8.9 GB | 16 GB+ | 34 |
| granite-4.1-8b-bf16 | bf16 | ≈ 16.8 GB | 24 GB+ | 38 |