PaddleOCR-VL-1.6-4bit

mlx-community/PaddleOCR-VL-1.6-4bit

Image Text to Text906M parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since October 8, 2026View on Hugging Face ↗
Downloads 30D
843
Total downloads
1,288
Gained 7D
—
Gained 30D
—
Likes
1
Rank · tracked models
—
–this week
Parameters
906M
Last source update
Aug 12, 2026

Downloads over time

Daily gain between consecutive observations

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-08. Charts appear as daily observations accumulate.

Likes over time

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-08. Charts appear as daily observations accumulate.

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-10-08. Charts appear as daily observations accumulate.

Overview

PaddleOCR-VL-1.6-4bit is a image text to text model published by mlx-community. OpenModelStats has tracked the model since Oct 8, 2026, most recently observing it 2h ago.

Published
Aug 12, 2026
Last updated
Aug 12, 2026
Library
mlx
License
apache-2.0
Task
Image Text to Text
Parameters
905,601,648
Spaces
—
Derivative models
—
Velocity 7D/day
—
mlxsafetensorspaddleocr_vlocrdocument-parsingmultimodalvision-languageimage-text-to-textconversationalcustom_codebase_model:PaddlePaddle/PaddleOCR-VL-1.6base_model:quantized:PaddlePaddle/PaddleOCR-VL-1.6

Publisher

mlx-communityView publisher statistics →

Derived from PaddlePaddle/PaddleOCR-VL-1.6 (reported by the source; parent not yet tracked).

Similar models

Models similar to PaddleOCR-VL-1.6-4bit
ModelDL 30D
wayu-paxa-ocr-zerowayu-ai8,907
PaddleOCR-VL-1.6-MLX-8bitOpenGryd786
PaddleOCR-VL-1.6-mlx-8bitjmbarrancoidener311
NVIDIA-Nemotron-Parse-2.0nvidia101.7K
llava-onevision-qwen2-0.5b-ov-hfllava-hf495.3K
llava-onevision-qwen2-0.5b-si-hfllava-hf4,969