tawkeed-ocr

tawkeed-ocr is an Arabic-first OCR vision-language model built by Tawkeed, fine-tuned for on-device and edge AI deployment.

Forked from NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct and fine-tuned on Arabic document and scene-text data, this model delivers accurate Arabic optical character recognition running natively on Tawkeed devices.

Highlights

• Arabic-first OCR — trained and rigorously tested on Arabic documents, handwriting, and scene text
• Edge-optimized — tuned to run efficiently on Tawkeed edge hardware for real-time OCR
• Production-ready — validated on Tawkeed's Arabic OCR benchmark suite
• Vision-Language — understands both visual layout and Arabic text context

Model Details

Property	Value
Base Model	NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct
Language	Arabic (ar), English (en)
License	Apache 2.0
Task	Optical Character Recognition
Fine-tuning	Arabic document & scene-text data
Deployment	On-device / Edge / Cloud

Training

This model is fine-tuned for Arabic OCR through:

1. Fork of the Qari-OCR vision-language model
2. Fine-tuning on Arabic documents, printed text, and handwritten samples
3. Evaluation on Tawkeed's Arabic OCR benchmark suite

Tawkeed Model Family

A complete suite of Arabic AI models — from compact edge models to large-scale MoE — all fine-tuned and tested for Arabic.

Model	Size	Type
tawkeed-sa/tawkeed-0.8b	0.8b	Arabic LLM
tawkeed-sa/tawkeed-2b	2b	Arabic LLM
tawkeed-sa/tawkeed-4b	4b	Arabic LLM
tawkeed-sa/tawkeed-9b	9b	Arabic LLM
tawkeed-sa/tawkeed-27b	27b	Arabic LLM
tawkeed-sa/tawkeed-40b	40b	Arabic LLM
tawkeed-sa/tawkeed-27b-MLX	27b 8-bit	LLM — Apple Silicon (MLX)
tawkeed-sa/tawkeed-27b-GGUF	27b Q8_0	LLM — Ollama / llama.cpp
tawkeed-sa/tawkeed-ocr	—	OCR
tawkeed-sa/tawkeed-embedding	—	Embedding

About Tawkeed

Tawkeed builds Arabic-native AI that runs on the edge. Every model in the family is fine-tuned for Arabic, tested on Arabic benchmarks, and optimized for deployment on Tawkeed devices.

Built by Tawkeed.