PrismML
Ultra-dense ternary models that run frontier-scale intelligence on local devices
Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.
About
PrismML builds compressed ternary large language models designed for high intelligence density with lower memory, latency, and energy use. Its Bonsai line targets on-device and local deployment where full-precision frontier models are too large or costly to run.
- Website
- prismml.com
- Added via
- web
- Ownership
- unclaimed
Where to go
Products
- Bonsai 2 27B — Ternary 27B model (~5.9 GB) for local agentic coding and multimodal reasoning