Liquid AI Launches LFM2.5-2.6B: On-Device Agentic Model Outperforming Larger Counterparts
maximelabonne · x · 2026-08-04
Liquid AI has released LFM2.5-2.6B, now available on Hugging Face. Designed as an on-device agentic model, it plans, calls tools, and handles multi-step tasks entirely locally on phones, laptops, and robots, ensuring data privacy with near-zero marginal cost per run.
Built on a hybrid architecture pre-trained on 34T tokens, the model supports a 128K context length. The team highlights its balanced intelligence per watt and customizability on a single GPU. It demonstrates impressive performance, scoring 77.83 on ToolSandbox (beating Qwen3.5-9B) and outperforming models nearly 4x its size on benchmarks like Multi-IF and IFStruct.
Related event: Liquid AI Releases 2.6B On-Device Agent Model LFM2.5(18 posts)→
More from coding & agent
- ERP•AI launches headless SaaS with $0 seats that bills machines: $1 buys 4,000 record writes — rohanpaul_ai · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16