Tether AI Research introduces BotPsy, a small model for on-device tool use
Tether AI Research says BotPsy, a 0.8B-parameter model built on Qwen3.5-0.8B, is designed for function calling and agentic workflows that run on a device. The company says it roughly doubles the base model's scores, with BFCL v4 rising from 23.4 to 44.0 and τ-bench from 23.2 to 51.5, and that it beats Qwen3.5-2B-Think on five of six tool-use benchmarks. BotPsy will be released with open weights under the Apache 2.0 license for research and educational use, and the company says it still makes mistakes and is not intended for high-stakes use.