openbmb · First MLX build 13 Oct 2026
MiniCPM-V-4.7-1B
MLX
TextVision apache-2.0
A 1.6B parameter vision and text model from openbmb, with 9 MLX builds, from 4-bit to bf16.
- Parameters
- 1.6B From Hugging Face
- Quantisation
- 8-bit MiniCPM-V-4.7-1B-8bit
- Memory needed
- 6 GB Estimate, unified memory
- Download
- 2.8 GB Weights, estimated
- Downloads
- 853 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 6 GB at 8-bit
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-4.7-1B-8bit --image photo.jpg --prompt "Describe this image"MLX builds
9 on mlx-community| MiniCPM-V-4.7-1B-OptiQ-4bit | 4-bit | 567 MB | 3 GB | 428 |
|---|---|---|---|---|
| MiniCPM-V-4.7-1B-4bit | 4-bit | 2.7 GB | 5 GB | 731 |
| MiniCPM-V-4.7-1B-mxfp4 | MXFP4 | 2.7 GB | 5 GB | 182 |
| MiniCPM-V-4.7-1B-nvfp4 | 4-bit | 2.7 GB | 5 GB | 179 |
| MiniCPM-V-4.7-1B-5bit | 5-bit | 2.7 GB | 6 GB | 176 |
| MiniCPM-V-4.7-1B-6bit | 6-bit | 2.7 GB | 6 GB | 230 |
| MiniCPM-V-4.7-1B-8bit | 8-bit | 2.8 GB | 6 GB | 853 |
| MiniCPM-V-4.7-1B-mxfp8 | MXFP8 | 2.8 GB | 6 GB | 250 |
| MiniCPM-V-4.7-1B-bf16 | bf16 | 3.1 GB | 6 GB | 360 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.