8-bit Open on Hugging Face
Parameters
35B
Weights (est.)
≈ 39.8 GB
Mac memory (est.)
48 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-4.7-35B-A3B-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- openbmb/MiniCPM-V-4.7-35B-A3B (quantized)
- Vendor
- openbmb
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 446 in the last 30 days · 446 all time · 1 likes
- Published
- 2026-10-13 · updated 2026-10-13 (29d ago)
- Tags
- minicpmv4_7, mlx-vlm, vision, multimodal, 8bit
Other MLX builds of openbmb/MiniCPM-V-4.7-35B-A3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiniCPM-V-4.7-35B-A3B-OptiQ-4bit | 4-bit | ≈ 20.6 GB | 32 GB+ | 792 |
| MiniCPM-V-4.7-35B-A3B-mxfp4 | MXFP4 | ≈ 23.5 GB | 32 GB+ | 2.0K |
| MiniCPM-V-4.7-35B-A3B-4bit | 4-bit | ≈ 23.5 GB | 32 GB+ | 922 |
| MiniCPM-V-4.7-35B-A3B-nvfp4 | 4-bit | ≈ 23.5 GB | 32 GB+ | 564 |
| MiniCPM-V-4.7-35B-A3B-5bit | 5-bit | ≈ 27.6 GB | 48 GB+ | 353 |
| MiniCPM-V-4.7-35B-A3B-6bit | 6-bit | ≈ 31.7 GB | 48 GB+ | 434 |
| MiniCPM-V-4.7-35B-A3B-mxfp8 | MXFP8 | ≈ 39.8 GB | 48 GB+ | 962 |
| MiniCPM-V-4.7-35B-A3B-8bit (this one) | 8-bit | ≈ 39.8 GB | 48 GB+ | 446 |
| MiniCPM-V-4.7-35B-A3B-bf16 | bf16 | ≈ 70.4 GB | 96 GB+ | 507 |