stepfun-ai · First MLX build 14 Aug 2026
GOT-OCR2_0
MLX
TextVision apache-2.0
A 561M parameter vision and text model from stepfun-ai, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 561M From Hugging Face
- Quantisation
- 4-bit GOT-OCR2_0-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 454 MB Weights, estimated
- Downloads
- 369 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 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/GOT-OCR2_0-4bit --image photo.jpg --prompt "Describe this image"MLX builds
3 on mlx-community| GOT-OCR2_0-4bit | 4-bit | 454 MB | 3 GB | 369 |
|---|---|---|---|---|
| GOT-OCR2_0-8bit | 8-bit | 686 MB | 3 GB | 64 |
| GOT-OCR2_0-bf16 | bf16 | 1.1 GB | 4 GB | 62 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.