OpenRouter (@OpenRouter) · 10/14/2026, 02:00:00
Liquid AI Releases LFM2.5-24B-A2B: A 24B MoE with 2B Active Parameters Optimized for Local Agent Tasks
Liquid AI has released LFM2.5-24B-A2B, its largest model to date, designed as an efficient Mixture-of-Experts (MoE) solution for laptops and PCs. With 24B total parameters but only 2B active per token, it supports a 131K context window and performs competitively against larger models like Qwen3.6-35B-A3B in agentic and tool-use tasks. Both base and post-trained weights are now available on Hugging Face and accessible via OpenRouter.
SOURCE COVERAGEFull Original Report
LFM2.5-24B-A2B from @liquidai is now on OpenRouter.
A 24B MoE with 2B active parameters that reasons before it answers, built for agents and tool use.
↳ 引用 @liquidai (Liquid AI): Today we release 𝙻𝙵𝙼𝟸.𝟻-𝟸𝟺𝙱-𝙰𝟸𝙱, the largest 𝙻𝙵𝙼𝟸.𝟻 family member. It is an efficient local model for laptops and PCs to work through multi-step tasks inside popular agent harnesses.
24B total parameters, 2B active per token Context expanded to 131K tokens A 128K-token vocabulary 33T pretraining tokens It is a reasoning model Very easy to fine-tune and customize Performs competitively with Qwen3.6-35B-A3B, a model with ~50% more total and active parameters, on agentic and tool-use tasks. Open base and post-trained weights on @huggingface 🤗
1/