4-bit Open on Hugging Face
Parameters
1.1B
Weights (est.)
≈ 608 MB
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/MiniCPM5-1B-4bit --prompt "Hello"
Details
- Base model
- openbmb/MiniCPM5-1B (quantized)
- Vendor
- openbmb
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 198 in the last 30 days · 2.4K all time · 1 likes
- Published
- 2026-05-26 · updated 2026-05-26 (5mo ago)
- Languages
- en, zh
- Tags
- llama, minicpm, minicpm5, long-context, tool-calling, on-device, edge-ai
Other MLX builds of openbmb/MiniCPM5-1B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiniCPM5-1B-OptiQ-4bit | 4-bit | ≈ 608 MB | 8 GB+ | 1.5K |
| MiniCPM5-1B-4bit (this one) | 4-bit | ≈ 608 MB | 8 GB+ | 198 |
| MiniCPM5-1B-mlx-6Bit | 6-bit | ≈ 878 MB | 8 GB+ | 1.4K |
| MiniCPM5-1B-8bit | 8-bit | ≈ 1.1 GB | 8 GB+ | 161 |