Edge LLM Distillation
Developed for
Mobile, kiosk, and on-prem teams that cannot ship large teacher models
The challenge
- Teacher models are too large for phones and thin clients
- Naive quantization destroys Arabic task quality
- Need a research path from teacher → student → on-device RAG
The Solution
Distillation and compression recipes aimed at Arabic edge deployments, pairing with SLLM releases and on-device RAG so students remain useful under tight memory budgets.
Key capabilities include:
- ◇ Compression and distillation for Arabic workloads
- ◇ CPU/mobile-oriented inference targets
- ◇ Integrated with GPU Lab capacity planning
Impact
Makes Arabic AI viable on the hardware customers already have in the field.
Organization benefits:
- Lower unit economics for edge assistants
- Broader device coverage
- Aligned research track with SLLM and RAG
Tags
Research Team
Meet Our PIs
Discover the principal investigator behind this project and the expertise that made it possible.
Hamza Salem
Head of PYXON Labs
Leads PYXON Labs research across Arabic AI, edge systems, governance, and applied products that ship into real environments.
// Open Vacancies
Join as a Scientist
Join our team working on Edge LLM Distillation. Explore opportunities in machine learning, Arabic NLP, computer vision, edge systems, and applied AI research.
View Open PositionsApply to this project
Submit the same scientist application used on PYXON Labs — tell us about your CV and how you’d contribute to Edge LLM Distillation.
Or email info@pyxon.com
Related Projects
Explore more PYXON Labs research connected to this work.