PrismML releases Bonsai 2 on-device ternary models
PrismML launched Bonsai 2, open-weight ternary models in 2B, 4B and 9B sizes, with the 2B running at 90 tokens/sec on an iPhone 17 Pro Max and supporting reasoning, vision and tool calling on-device.
🚨 JUST LAUNCHED: Bonsai 2 from @PrismML. Open-weight ternary models in 2B, 4B and 9B, small enough to run on a phone. The 2B hits 90 tokens/sec on iPhone 17 Pro Max, with reasoning, vision and tool calling all on-device. You can try Bonsai 2 9B today on @DarkbloomAI, where the first 100 people get 250M free tokens. And we’re making it faster on @YukonResearch. Bonsai 2 9B runs at 170+ tokens/sec at launch. There are two tracks, Apple Silicon on http://mlx.fast and NVIDIA DGX Spark on http://cuda.fast. To join, pick a track, point your agent at it and submit a faster run. Every new best is open for anyone to build on.
This post quotes another post: x.com/prismml/status/2110823964650164348