BotPsy: Tether Ships an 0.8B Agentic Model That Beats 2B Rivals
Tether AI just released BotPsy, an 800M-parameter tool-calling model that outperforms Qwen 2B on five of six agentic benchmarks. The kicker? It's designed to run entirely on your phone.
3 posts
Tether AI just released BotPsy, an 800M-parameter tool-calling model that outperforms Qwen 2B on five of six agentic benchmarks. The kicker? It's designed to run entirely on your phone.
Liquid AI's new model runs reasoning agents on-device at 184 tok/s on an M5 Max. It beats models with 50% more parameters on tool-use tasks while keeping memory and compute absurdly low.
Liquid AI just released DSpark draft models for three LFM2.5 checkpoints, delivering GPU and on-device speedups via speculative decoding—without touching output quality. Here's how it works.