8-bit Open on Hugging Face
Parameters
8.2B
Weights (est.)
≈ 8.7 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/MiniCPM4.1-8B-8bit --prompt "Hello"
Details
- Base model
- openbmb/MiniCPM4.1-8B (quantized)
- Vendor
- openbmb
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 33 in the last 30 days · 794 all time · 1 likes
- Published
- 2025-09-08 · updated 2025-09-08 (1y ago)
- Languages
- zh, en
- Tags
- minicpm, custom_code
Other MLX builds of openbmb/MiniCPM4.1-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiniCPM4.1-8B-4bit | 4-bit | ≈ 4.6 GB | 8 GB+ | 62 |
| MiniCPM4.1-8B-6bit | 6-bit | ≈ 6.7 GB | 16 GB+ | 29 |
| MiniCPM4.1-8B-8bit (this one) | 8-bit | ≈ 8.7 GB | 16 GB+ | 33 |
| MiniCPM4.1-8B-bf16 | bf16 | ≈ 16.4 GB | 24 GB+ | 30 |