4-bit Open on Hugging Face
Parameters
3.9B
Weights (est.)
≈ 2.2 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/Nanbeige4.1-3B-4bit --prompt "Hello"
Details
- Base model
- Nanbeige/Nanbeige4.1-3B (quantized)
- Vendor
- Nanbeige
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 74 in the last 30 days · 863 all time · 1 likes
- Published
- 2026-02-23 · updated 2026-02-23 (8mo ago)
- Languages
- en, zh
- Tags
- llama, nanbeige
Other MLX builds of Nanbeige/Nanbeige4.1-3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Nanbeige4.1-3B-4bit (this one) | 4-bit | ≈ 2.2 GB | 8 GB+ | 74 |
| Nanbeige4.1-3B-8bit | 8-bit | ≈ 4.2 GB | 8 GB+ | 1.3K |
| Nanbeige4.1-3B-bf16 | bf16 | ≈ 7.9 GB | 16 GB+ | 58 |