dots-studio · First MLX build 28 Mar 2026
dots.mocr
MLX
TextVision mit
A 3B parameter vision and text model from dots-studio, with 7 MLX builds, from 4-bit to MXFP8.
- Parameters
- 3B From Hugging Face
- Quantisation
- 8-bit dots.mocr-8bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.4 GB Weights, estimated
- Downloads
- 228 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 7 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/dots.mocr-8bit --image photo.jpg --prompt "Describe this image"MLX builds
7 on mlx-community| dots.mocr-4bit | 4-bit | 3.5 GB | 6 GB | 152 |
|---|---|---|---|---|
| dots.mocr-nvfp4 | 4-bit | 3.5 GB | 6 GB | 50 |
| dots.mocr-mxfp4 | MXFP4 | 3.5 GB | 6 GB | 40 |
| dots.mocr-5bit | 5-bit | 3.7 GB | 7 GB | 39 |
| dots.mocr-6bit | 6-bit | 4.0 GB | 7 GB | 36 |
| dots.mocr-8bit | 8-bit | 4.4 GB | 7 GB | 228 |
| dots.mocr-mxfp8 | MXFP8 | 4.4 GB | 7 GB | 52 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.