Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

RELEASE · MODELS · #3385

Tether AI Research releases BotPsy 0.8B — an on-device agentic personal assistant

Tether AI Research unveiled BotPsy, a 0.8‑billion‑parameter language model based on Qwen3.5-0.8B designed for function-calling and agentic workflows for on-device deployment. The team reports BotPsy achieves state-of-the-art tool-use and multi-turn agentic performance among models ≤1.2B parameters on benchmarks including BFCL v4, ACEBench and τ-bench, while offering improved instruction-following and lower automated red-teaming unsafe rates; it is intended for low-to-medium difficulty tasks and not for high-stakes use.

KEY POINTS

  1. Tether AI Research unveiled BotPsy, a 0.8‑billion‑parameter language model based on Qwen3.5-0.8B designed for function-calling and agentic workflows for on-device deployment.
  2. The team reports BotPsy achieves state-of-the-art tool-use and multi-turn agentic performance among models ≤1.2B parameters on benchmarks including BFCL v4, ACEBench and τ-bench, while offering improved instruction-following and lower automated red-teaming unsafe rates; it is intended for low-to-medium difficulty tasks and not for high-stakes use.
  3. A compact, high-performing agentic model optimized for on-device tool use could shift some assistant and automation workloads away from costly cloud LLMs, improving privacy and deployment control.

WHY IT MATTERS

A compact, high-performing agentic model optimized for on-device tool use could shift some assistant and automation workloads away from costly cloud LLMs, improving privacy and deployment control.

SOURCES & TIMELINE

1