Liquid AI Launches LFM2.5: 2.6B Parameter On-Device Agentic Model
JosephJacks_ · x · 2026-08-04
Liquid AI has released the new LFM2.5-2.6B model. Designed as an on-device agentic model, it can plan, call tools, and work through multi-step tasks entirely locally on phones, laptops, and robots, keeping data on-device with essentially zero marginal cost per run.
Built on the LFM2.5 flagship hybrid architecture and pre-trained on 34T tokens, the model supports a 128K context length. Official benchmarks show highly impressive performance, comparable to or better than models nearly 4x its size, such as Qwen3.5-9B and Gemma-4-E4B-it.
Related event: Liquid AI Launches LFM2.5-2.6B On-Device Agent Model(5 posts)→
More from Infra
- Open-Source 'Personal AI Computer': Build a Local AI Data Center with RTX 5090s — dee_hw · 2026-08-05
- AI Compute Demand to Quadruple Data Center Electricity by 2030 — bittingthembits · 2026-08-05
- DeepSeek V4 Flash Local Deployment Hits 16k Output Limit — El_90 · 2026-08-05
- China's Potential InP Wafer Export Ban Threatens Global AI Infrastructure — teortaxesTex · 2026-08-05
- 3-Hour Deep Dive with vLLM Core Dev: Open Source Infra and Model Co-design — vista8 · 2026-08-05
- Running MiniMax H3 on a Single 3090: Troubleshooting OOMs and Optimizing Args — knoll_gallagher · 2026-08-05