Liquid AI Launches LFM2.5-2.6B: An On-Device Agentic Model
JosephJacks_ · x · 2026-08-06
Liquid AI has released the LFM2.5-2.6B model, focusing on agentic capabilities that run entirely on-device. It can plan, call tools, and execute multi-step tasks on phones, laptops, and robots, ensuring data privacy and near-zero marginal costs.
Key Specs:
- Pre-trained on approximately 34T tokens.
- Features the flagship LFM2.5 hybrid architecture.
- Context length and vocabulary size are both 128K.
- Balanced intelligence per watt, customizable on a single GPU.
Performance:
The model achieves comparable or better scores than models nearly 4x its size. For instance, it scores 77.83 on ToolSandbox (beating Qwen3.5-9B at 76.44) and 80.07 on Multi-IF (outperforming Gemma-4-E4B-it at 77.35).
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