PrismML

AI startup founded by Caltech researchers, focused on extreme model compression for edge deployment. Emerged from stealth in April 2026 with a $16.25 million seed round and the Bonsai 1-bit LLM family — models where every weight is represented by its sign ({-1, +1}) plus a shared scale factor, trained natively at 1-bit precision end-to-end. The flagship Bonsai 8B fits in 1.15 GB and runs 8x faster than full-precision equivalents on edge hardware. Models released under Apache 2.0.

Timeline

• 2026-04-06-AI-Digest — PrismML emerged from stealth with $16.25M seed round and the open-source Bonsai 1-bit LLM family (8B, 4B, 1.7B) under Apache 2.0, enabling competitive edge inference at a fraction of typical memory requirements.

Context

• Related to MOC - Open Source Models — Bonsai models released under Apache 2.0
• Related to MOC - AI Infrastructure — Extreme compression enabling edge and on-device inference
• Related to Gemma 4 — Competing in the on-device/edge AI space