PrismML 发布 Bonsai 2 端侧三值模型
2B/4B/9B 开放权重三值模型，2B 在 iPhone 17 Pro Max 上跑到 90 tok/s，支持推理、视觉与工具调用，全部本地运行。
🚨 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.
这条是引用着另一条写的：x.com/prismml/status/2110823964650164348