MLX Community · First MLX build 22 Oct 2025
olmOCR-2-7B-1025
MLX
TextVision apache-2.0
A 8.3B parameter vision and text model, with 7 MLX builds, from bf16 to 5-bit.
- Parameters
- 8.3B From Hugging Face
- Quantisation
- 8-bit olmOCR-2-7B-1025-mlx-8bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 240K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 7 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/olmOCR-2-7B-1025-mlx-8bit --image photo.jpg --prompt "Describe this image"MLX builds
7 on mlx-community| olmOCR-2-7B-1025-bf16 | bf16 | 16.6 GB | 21 GB | 1.1K |
|---|---|---|---|---|
| olmOCR-2-7B-1025-mlx-8bit | 8-bit | — | — | 240K |
| olmOCR-2-7B-1025-mlx-4bit | 4-bit | — | — | 1.2K |
| olmOCR-2-7B-1025-4bit | 4-bit | — | — | 1.1K |
| olmOCR-2-7B-1025-8bit | 8-bit | — | — | 1.1K |
| olmOCR-2-7B-1025-6bit | 6-bit | — | — | 418 |
| olmOCR-2-7B-1025-5bit | 5-bit | — | — | 412 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.