Liquid AI 的 LFM2.5-24B-A2B 上线 OpenRouter
LFM2.5-24B-A2B from @liquidai is now on OpenRouter.
来自 @liquidai 的 LFM2.5-24B-A2B 现已上线 OpenRouter。 一个 24B MoE、2B 激活参数，先推理再作答，专为智能体和工具使用打造。
查看原帖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 >…
展开完整原文
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/
正文
当前显示原文，中文全文译文尚未就绪。
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.