openbmb · First MLX build 13 Oct 2026
MiniCPM-V-4.7-35B-A3B
MLX
TextVision apache-2.0
A 35B parameter vision and text model from openbmb, with 9 MLX builds, from 4-bit to bf16.
- Parameters
- 35B From Hugging Face
- Quantisation
- MXFP4 MiniCPM-V-4.7-35B-A3B-mxfp4
- Memory needed
- 29 GB Estimate, unified memory
- Download
- 23.5 GB Weights, estimated
- Downloads
- 1.9K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 9 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 29 GB at MXFP4
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4 --image photo.jpg --prompt "Describe this image"MLX builds
9 on mlx-community| MiniCPM-V-4.7-35B-A3B-OptiQ-4bit | 4-bit | 20.6 GB | 26 GB | 759 |
|---|---|---|---|---|
| MiniCPM-V-4.7-35B-A3B-mxfp4 | MXFP4 | 23.5 GB | 29 GB | 1.9K |
| MiniCPM-V-4.7-35B-A3B-4bit | 4-bit | 23.5 GB | 29 GB | 792 |
| MiniCPM-V-4.7-35B-A3B-nvfp4 | 4-bit | 23.5 GB | 29 GB | 483 |
| MiniCPM-V-4.7-35B-A3B-5bit | 5-bit | 27.6 GB | 33 GB | 298 |
| MiniCPM-V-4.7-35B-A3B-6bit | 6-bit | 31.7 GB | 38 GB | 357 |
| MiniCPM-V-4.7-35B-A3B-mxfp8 | MXFP8 | 39.8 GB | 47 GB | 763 |
| MiniCPM-V-4.7-35B-A3B-8bit | 8-bit | 39.8 GB | 47 GB | 389 |
| MiniCPM-V-4.7-35B-A3B-bf16 | bf16 | 70.4 GB | 81 GB | 447 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.