6-bit Open on Hugging Face
Parameters
4.3B
Weights (est.)
≈ 3.5 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/MiniCPM3-4B-6bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/OpenBNB-MiniCPM3-4b (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 32 in the last 30 days · 306 all time · 0 likes
- Published
- 2025-03-19 · updated 2025-03-19 (1y ago)
- Languages
- zh, en
- Tags
- minicpm3, custom_code
Other MLX builds of Goekdeniz-Guelmez/OpenBNB-MiniCPM3-4b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiniCPM3-4B-6bit (this one) | 6-bit | ≈ 3.5 GB | 8 GB+ | 32 |
| MiniCPM3-4B-8bit | 8-bit | ≈ 4.5 GB | 8 GB+ | 41 |
| MiniCPM3-4B-bfloat16 | — | ≈ 8.5 GB | 16 GB+ | 32 |