- Intelligence Density: PrismML focuses on “intelligence density,” building ultra-dense models that maximize performance while minimizing size and energy consumption.
- 1-Bit Bonsai Architecture: The company has launched the first commercially viable 1-bit weight LLM family (Bonsai 8B, 4B, and 1.7B), which uses sign-based weights to achieve massive compression.
- Efficiency Gains: Their 8B model is 14x smaller, 8x faster, and 5x more energy-efficient than full-precision counterparts while remaining competitive on benchmarks.
- Edge & Robotics Focus: Designed for local execution, these models enable on-device AI agents, real-time robotics, and IoT applications without cloud dependency.
Entities: Babak Hassibi (Co-Founder & CEO, Sahin Lale (Co-Founder & Co-Head of Research, Omead Pooladzandi (Co-Founder & Co-Head of Research, Reza Sadri (Co-Founder & VP Strategy, Shayan Ilbagian (CFO, Karim Mattar (VP Engineering, Tushar Bansal (Director, Product, Ion Stoica (Advisor, Buno Pati (Advisor, Julie Schoenfeld (Advisor, PrismML (Prism ML, Inc, Caltech (California Institute of Technology