openbmb · First MLX build 11 May 2026
MiniCPM-V-4.6
MLX
TextVision apache-2.0
A 1.3B parameter vision and text model from openbmb, with 7 MLX builds, from 4-bit to bf16.
- Parameters
- 1.3B From Hugging Face
- Quantisation
- 4-bit MiniCPM-V-4.6-4bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.2 GB Weights, estimated
- Downloads
- 404 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 7 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at 4-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-4.6-4bit --image photo.jpg --prompt "Describe this image"MLX builds
7 on mlx-community| MiniCPM-V-4.6-4bit | 4-bit | 2.2 GB | 5 GB | 404 |
|---|---|---|---|---|
| MiniCPM-V-4.6-mxfp4 | MXFP4 | 2.2 GB | 5 GB | 28 |
| MiniCPM-V-4.6-nvfp4 | 4-bit | 2.2 GB | 5 GB | 26 |
| MiniCPM-V-4.6-5bit | 5-bit | 2.2 GB | 5 GB | 44 |
| MiniCPM-V-4.6-8bit | 8-bit | 2.3 GB | 5 GB | 70 |
| MiniCPM-V-4.6-mxfp8 | MXFP8 | 2.3 GB | 5 GB | 56 |
| MiniCPM-V-4.6-bf16 | bf16 | 2.6 GB | 5 GB | 185 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.