MLX Community · First MLX build 26 Oct 2025
DeepSeek-OCR
MLX
TextVision mit Trending
A 3.3B parameter vision and text model, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 3.3B From Hugging Face
- Quantisation
- 8-bit DeepSeek-OCR-8bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 3.9 GB Weights, estimated
- Downloads
- 1.7K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 5 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/DeepSeek-OCR-8bit --image photo.jpg --prompt "Describe this image"MLX builds
5 on mlx-community| DeepSeek-OCR-4bit | 4-bit | 2.5 GB | 5 GB | 394 |
|---|---|---|---|---|
| DeepSeek-OCR-5bit | 5-bit | 2.8 GB | 6 GB | 63 |
| DeepSeek-OCR-6bit | 6-bit | 3.2 GB | 6 GB | 83 |
| DeepSeek-OCR-8bit | 8-bit | 3.9 GB | 7 GB | 1.7K |
| DeepSeek-OCR-bf16 | bf16 | 6.7 GB | 10 GB | 127 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.