Liquid AI Launches LFM2.5-2.6B: An On-Device Agentic Model
JosephJacks_ · x · 2026-08-06
Liquid AI has officially released LFM2.5-2.6B, an agentic model designed to run entirely on-device. It can plan, call tools, and work through multi-step tasks on phones, laptops, PCs, and robots while keeping data completely local.
Key Specs:
- Pre-trained on 34T tokens using the LFM2.5 flagship hybrid architecture.
- Supports 128K context length and a 128K vocabulary size.
- Offers balanced intelligence per watt, customizable on a single GPU, with LFM2 open-weight license.
Performance:
- Quantized (Q4) size is under 1.7GB, enabling it to run directly on smartphones.
- Achieves comparable or better scores than models up to 4x its size, such as Qwen3.5-9B and Gemma-4-E4B-it, on benchmarks like ToolSandbox and Multi-IF.
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