tawkeed-9b

tawkeed-9b is an Arabic-first language model built by Tawkeed, fine-tuned for on-device and edge AI deployment.

Forked from Qwen/Qwen3.5-9B and fine-tuned on large-scale Arabic corpora, this model is optimized to run natively on Tawkeed devices — delivering fast, private, Arabic-language AI at the edge.

Highlights

  • Arabic-first — trained and rigorously tested on Arabic text across diverse domains
  • Edge-optimized — sized and tuned to run efficiently on Tawkeed edge hardware
  • Production-ready — validated on Tawkeed's Arabic benchmark suite for real-world accuracy
  • Bilingual — retains strong English capability from the base model

Model Details

Property Value
Base Model Qwen/Qwen3.5-9B
Parameters 9b
Language Arabic (ar), English (en)
License Apache 2.0
Fine-tuning Continued pretraining + SFT on Arabic data
Deployment On-device / Edge / Cloud

Training

This model is fine-tuned through a multi-stage Arabic enhancement pipeline:

  1. Continued pretraining on Arabic corpora — Wikipedia, CulturaX, OSCAR
  2. Supervised fine-tuning (SFT) on curated Arabic instruction datasets — OALL, Alpaca-GPT4-Arabic, Aya
  3. Evaluation on Tawkeed's Arabic benchmark suite to ensure quality across generation, comprehension, and reasoning tasks

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("tawkeed-sa/tawkeed-9b")
tokenizer = AutoTokenizer.from_pretrained("tawkeed-sa/tawkeed-9b")

messages = [{"role": "user", "content": "ما هي عاصمة المملكة العربية السعودية؟"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

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.

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.

Downloads last month
46
Safetensors
Model size
10B params
Tensor type
BF16
·
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tawkeed-sa/tawkeed-9b

Finetuned
Qwen/Qwen3.5-9B
Finetuned
(109)
this model
Quantizations
2 models