hayulalab/averroes-q-training-paper

Averroes-Q: Training a 32-Billion Parameter Bilingual Arabic-English LLM on a Single Apple M2 Ultra Workstation — Hayula Research

Hayula AI Lab

Abstract

We present Averroes-Q, a 32-billion parameter bilingual Arabic-English large language model fine-tuned entirely on a single Apple M2 Ultra workstation with 192 GB of unified memory. Built upon the Qwen2.5-32B-Instruct architecture, Averroes-Q is the first publicly released Arabic-capable LLM trained exclusively on consumer-grade Apple Silicon hardware. Using parameter-efficient fine-tuning via Low-Rank Adaptation (LoRA) and Apple's MLX framework, we demonstrate that a complete bilingual instruct

Files

File	Description
paper.md	Full paper (Markdown)
README.md	This model card

Citation

@techreport{hayulalab2026averroesqtraining,
    title={Averroes-Q: Training a 32-Billion Parameter Bilingual Arabic-English LLM on a Single Apple M2 Ultra Workstation — Hayula Research},
    author={Hayula AI Lab},
    year={2026},
    url={https://huggingface.co/hayulalab/averroes-q-training-paper}
}

---

hayulalab — Open Source AI Research