Qari-OCR-0.4.0-VL-4B-Instruct

NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct

Image to TextpeftLicense: apache-2.0
Tracked by OpenModelStats since September 16, 2026View on Hugging Face ↗
Downloads 30D
1,184
Total downloads
4,615
Gained 7D
—
Gained 30D
—
Likes
10
Rank · tracked models
#31,318
56(down 56 places)this week
Parameters
—
Last source update
Feb 1, 2026
Momentum
0.0

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Qari-OCR-0.4.0-VL-4B-Instruct is a image to text model published by NAMAA-Space. OpenModelStats has tracked the model since Sep 16, 2026, most recently observing it Oct 5, 2026.

Published
Dec 28, 2025
Last updated
Feb 1, 2026
Library
peft
License
apache-2.0
Task
Image to Text
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
—
peftsafetensorsvisionocrarabicislamicqwen3fine-tunedimage-to-textardataset:seemorg/books-ocrbase_model:Qwen/Qwen3-VL-4B-Instruct

Publisher

NAMAA-SpaceView publisher statistics →

Derived from Qwen/Qwen3-VL-4B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to Qari-OCR-0.4.0-VL-4B-Instruct
ModelDL 30D
GLM-OCRzai-org1.8M
blip-image-captioning-baseSalesforce1.5M
manga-ocr-basekha-white1.1M
blip-image-captioning-largeSalesforce583.3K
PP-OCRv5_server_detPaddlePaddle522.6K
UVDocPaddlePaddle468.2K
NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct — Downloads, Growth & Stats | OpenModelStats