Liquid AI ships LFM2.5-2.6B, a small fast model built for on-device agents on phones and laptops
helloiamleonie · x · 2026-09-25
Liquid AI's LFM2.5-2.6B model is now available on Hugging Face, with the team inviting developers to run it on their laptops and phones for on-device agent experiments.
- Positioned as small, fast, and optimized for agentic tasks, with a built-in tool-calling chat template.
- The pitch: local agents run on phones, laptops, robots, and cars — for free, all day in the background, with multiple agents running in parallel.
- Aimed at offline/on-device autonomous agent development; the team asks users to share what they build.
Related event: Liquid AI Releases LFM2.5-2.6B and Details Its On-Device Training Recipe(10 posts)→
More from Infra
- Your data stack is about to get less forgiving: agents turn stale data into wrong actions — bigdata · 2026-09-25
- Bending Spoons runs 99% of AI traffic on self-hosted open models, thanks to evals — alex_verem · 2026-09-25
- Splash on a 40-core M5 Max: +20% decode speed by running tune-kernels on your own chip — SeveralViolins · 2026-09-25
- 100-agent doc review fan-out finishes in 10 minutes for $5.75, open-source harness holds — Pitiful-Surround-285 · 2026-09-25
- Nvidia's UHP laser demand ramps for December quarter as Spectrum-6 CPO beats plan, says Lumentum — firstadopter · 2026-09-25
- Lambda's Stephen Balaban on 14 years, 5 pivots, and debunking data center myths — gharik · 2026-09-25