6-bit Open on Hugging Face
Parameters
2.5B
Weights (est.)
≈ 2.1 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-3.3-2b-instruct-6bit --prompt "Hello"
Details
- Base model
- ibm-granite/granite-3.3-2b-instruct (quantized)
- Vendor
- IBM · Granite
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 21 in the last 30 days · 257 all time · 0 likes
- Published
- 2025-04-16 · updated 2025-04-16 (1y ago)
- Tags
- granite, language, granite-3.3
Other MLX builds of ibm-granite/granite-3.3-2b-instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| granite-3.3-2b-instruct-4bit | 4-bit | ≈ 1.4 GB | 8 GB+ | 768 |
| granite-3.3-2b-instruct-6bit (this one) | 6-bit | ≈ 2.1 GB | 8 GB+ | 21 |
| granite-3.3-2b-instruct-8bit | 8-bit | ≈ 2.7 GB | 8 GB+ | 89 |
| granite-3.3-2b-instruct-fp16 | fp16 | ≈ 5.1 GB | 8 GB+ | 32 |