Liquid AI Launches On-Device Agentic Model LFM2.5-2.6B
helloiamleonie · x · 2026-08-05
Liquid AI released LFM2.5-2.6B, a new on-device agentic model designed to run entirely locally on phones, laptops, and robots.
- Key Features: Operates fully on-device ensuring data privacy with essentially zero marginal cost per run. Capable of planning, tool calling, and multi-step tasks.
- Architecture & Specs: Utilizes the LFM2.5 flagship hybrid architecture, pre-trained on 34T tokens with a 128K context length.
- Performance: Can handle 32+ parallel sessions on a single GPU with aggregate throughput of hundreds of tokens/sec. Achieves scores comparable to or better than models nearly 4x its size (e.g., Qwen3.5-9B) in various benchmarks.
Related event: Liquid AI Releases 2.6B Edge Agent Model LFM2.5-2.6B(9 posts)→
More from Embodied
- Build a Desktop Robot for $8: Open-Source Xiaozhi Framework Brings Local AI to ESP32 — TinfoilTricorn · 2026-08-05
- Unitree IPO Filings Reveal ~60% Gross Margins, Flipping Hardware Commodity Myth — Rewkang · 2026-08-05
- Assemble Bench: A New Benchmark for Robot Models Based on NIST Standards — ycombinator · 2026-08-05
- Lukas Ziegler's Bet: First Scalable Humanoids Will Master Narrow Tasks Like Ship Welding — lukas_m_ziegler · 2026-08-05
- Recent Humanoid Robotics Papers: Wrench-Augmented Learning — carlosdponx · 2026-08-05
- Pandroid Unveils Affordable, Durable Robot Hardware for Embodied AI Data — chris_j_paxton · 2026-08-05