Pyxon SLLM v0
Developed for
Builders who need Arabic instruction-following locally—labs, kiosks, and air-gapped environments
The challenge
- Frontier Arabic quality usually requires large cloud models
- Edge hardware cannot host multi-tens-of-GB checkpoints
- Teams need a practical offline baseline to iterate RAG and agents
The Solution
Pyxon SLLM v0 is a small Arabic-capable instruction model released for local runtimes, sized for developer laptops and edge boxes while remaining useful as a RAG and agent backbone.
Key capabilities include:
- ◇ ~1.6 GB footprint suitable for Ollama and local stacks
- ◇ Arabic-focused instruction tuning for regional workloads
- ◇ Designed as a companion to on-device RAG and distillation research
Impact
Lowers the barrier to shipping offline Arabic AI demos and products without waiting on cloud quotas.
Organization benefits:
- Faster prototyping on local GPUs and CPUs
- Data stays inside the organization
- A shared baseline model across Labs projects
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 Pyxon SLLM v0. 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 Pyxon SLLM v0.
Or email info@pyxon.com
Related Projects
Explore more PYXON Labs research connected to this work.