Skip to content

PaddleOCR-VL-1.6-4bit

mlx-community/PaddleOCR-VL-1.6-4bit
4-bit Open on Hugging Face
Parameters
906M
Weights (est.)
≈ 703 MB
Mac memory (est.)
8 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Run it

With mlx-vlm on an Apple silicon Mac:

pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/PaddleOCR-VL-1.6-4bit --image photo.jpg --prompt "Describe this image"

Details

Base model
PaddlePaddle/PaddleOCR-VL-1.6 (quantized)
Vendor
PaddlePaddle
Task
Vision + text
Quantisation
4-bit
Licence
apache-2.0
Downloads
1.5K in the last 30 days · 3.0K all time · 3 likes
Published
2026-08-12 · updated 2026-08-12 (3mo ago)
Tags
paddleocr_vl, document-parsing, multimodal, vision-language, custom_code

Other MLX builds of PaddlePaddle/PaddleOCR-VL-1.6

Build Quantisation Weights Mac memory Downloads
PaddleOCR-VL-1.6-4bit (this one) 4-bit ≈ 703 MB 8 GB+ 1.5K
PaddleOCR-VL-1.6-5bit 5-bit ≈ 800 MB 8 GB+ 470