4-bit Open on Hugging Face
Parameters
1.0B
Weights (est.)
≈ 567 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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/MiniCPM-V-4.7-1B-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- openbmb/MiniCPM-V-4.7-1B (quantized)
- Vendor
- openbmb
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 442 in the last 30 days · 442 all time · 2 likes
- Published
- 2026-10-13 · updated 2026-10-13 (29d ago)
- Tags
- minicpmv4_7, optiq, quantized, 4bit, mixed-precision, minicpm-v, multimodal, vision-language-model, apple-silicon
Other MLX builds of openbmb/MiniCPM-V-4.7-1B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiniCPM-V-4.7-1B-OptiQ-4bit (this one) | 4-bit | ≈ 567 MB | 8 GB+ | 442 |
| MiniCPM-V-4.7-1B-4bit | 4-bit | ≈ 2.7 GB | 8 GB+ | 886 |
| MiniCPM-V-4.7-1B-mxfp4 | MXFP4 | ≈ 2.7 GB | 8 GB+ | 214 |
| MiniCPM-V-4.7-1B-nvfp4 | 4-bit | ≈ 2.7 GB | 8 GB+ | 200 |
| MiniCPM-V-4.7-1B-5bit | 5-bit | ≈ 2.7 GB | 8 GB+ | 197 |
| MiniCPM-V-4.7-1B-6bit | 6-bit | ≈ 2.7 GB | 8 GB+ | 258 |
| MiniCPM-V-4.7-1B-8bit | 8-bit | ≈ 2.8 GB | 8 GB+ | 956 |
| MiniCPM-V-4.7-1B-mxfp8 | MXFP8 | ≈ 2.8 GB | 8 GB+ | 302 |
| MiniCPM-V-4.7-1B-bf16 | bf16 | ≈ 3.1 GB | 8 GB+ | 390 |