Downloads · 30 days
20
11% of all-time downloads
Unlimited-OCR-4bit-mlx
mikoy92/Unlimited-OCR-4bit-mlx
Unlimited-OCR-4bit-mlx is a image-text-to-text model from mikoy92. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as mit.
This is a 4-bit affine MLX quantization of mikoy92/Unlimited-OCR-bf16-mlx, converted with mlx-vlm.
All-time downloads
180
Public
Parameters
3.3B
2.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.5 GB · 100%
Parameter types
How the weights are stored.
U322.9B · 88%
Base models
Model card
From the Hugging Face model README
Unlimited-OCR 4-bit MLX
This is a 4-bit affine MLX quantization of mikoy92/Unlimited-OCR-bf16-mlx, converted with mlx-vlm.
Quantization settings:
- mode:
affine - bits:
4 - group size:
64 - observed effective bits per weight during conversion:
5.883
Because this is a vision-language OCR model, mlx-vlm does not aggressively quantize every multimodal tensor; the effective bits-per-weight can be higher than exactly 4-bit.
Usage
pip install -U mlx-vlm
mlx_vlm.generate \
--model mikoy92/Unlimited-OCR-4bit-mlx \
--image /path/to/image.png \
--prompt "Extract all readable text from this image." \
--max-tokens 512 \
--temperature 0
Validation
Before upload, this checkpoint was loaded locally with mlx_vlm.generate and produced OCR text/table output on a document-image smoke test.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- deepseekocr
- License
- mit
- Languages
- multilingual
- Created
- Jun 23, 2026
- Updated
- Jun 23, 2026