MLX Community · First MLX build 11 Nov 2025
LightOnOCR-1B-1025
MLX
Vision apache-2.0
A 1.2B parameter image to text model, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 1.2B From Hugging Face
- Quantisation
- bf16 LightOnOCR-1B-1025-bf16
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.3 GB Weights, estimated
- Downloads
- 35 This build, last 30 days
- Task
- Image to text Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at bf16
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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/LightOnOCR-1B-1025-bf16MLX builds
5 on mlx-community| LightOnOCR-1B-1025-4bit | 4-bit | 1.2 GB | 4 GB | 22 |
|---|---|---|---|---|
| LightOnOCR-1B-1025-5bit | 5-bit | 1.3 GB | 4 GB | 14 |
| LightOnOCR-1B-1025-6bit | 6-bit | 1.4 GB | 4 GB | 13 |
| LightOnOCR-1B-1025-8bit | 8-bit | 1.6 GB | 4 GB | 11 |
| LightOnOCR-1B-1025-bf16 | bf16 | 2.3 GB | 5 GB | 35 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.