← Library · Frontier

Liquid AI Releases LFM2.5-2.6B for High-Volume Agentic Workloads

Liquid AI has introduced LFM2.5-2.6B, a compact model optimized for high-volume agentic workloads. This model excels in instruction-following and tool-use benchmarks, outperforming Gemma models and trading closely with Qwen models on agentic tasks. While larger models maintain an edge in coding, LFM2.5-2.6B demonstrates strong performance in STEM fields, leading on AA-Omniscience-Public.

Why it matters

LFM2.5-2.6B offers a powerful yet efficient solution for deploying AI agents in high-volume scenarios, enabling more widespread and cost-effective application of agentic AI.

Learn one new AI thing every day.

Daily Deck sends you seven plain-English cards like this every morning. Free.

Start free