@maximelabonne: Agentic intelligence too cheap to meter: LFM2.5-24B-A2B is competitive with much bigger MoEs and incredibly fast Very p…
Summary
Liquid AI 发布 LFM2.5-24B-A2B，采用 24B 总参数、每 token 仅激活 2B 的 MoE 架构，主打本地设备上的高效多步 Agent 任务，并将上下文扩展到 131K tokens。
View Cached Full Text
Cached at: 10/13/26, 05:45 PM
Agentic intelligence too cheap to meter: LFM2.5-24B-A2B is competitive with much bigger MoEs and incredibly fast
Very proud of this one, the team cooked 🧑🍳
Liquid AI (@liquidai): 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 >
Similar Articles
Run fast, private agents on-device with LFM2.5-24B-A2B
Liquid AI 发布 LFM2.5-24B-A2B，一个 24B 总参数、仅 2B 激活参数的推理型 MoE 模型，专为在本地设备上运行快速、私密的智能体而设计，在工具使用和智能体任务上可与参数量多约 50% 的模型竞争。
LFM2.5-24B-A2B (7 minute read)
Liquid AI 发布 LFM2.5-24B-A2B，一个 24B 参数、仅 2B 激活参数的开源权重推理模型，专为快速、私密的设备端智能体设计，在多个智能体与工具使用基准上超越更大的 MoE 模型。
@maximelabonne: LFM2.5-2.6B is available today on @huggingface First agentic model of its kind, it destroys our previous release on EVE…
Liquid AI released LFM2.5-2.6B, an on-device agentic model that plans, calls tools, and works through multi-step tasks on phones, laptops, PCs, and robots, with data never leaving the device.
Liquid AI reveals 8B-A1B MoE trained on 38T
Liquid AI released LFM2.5-8B-A1B, an edge MoE model trained on 38T tokens with a 128K context window, improved tool calling, and reasoning capabilities, available on Hugging Face.
@liquidai: Introducing LFM2.5-230M: our smallest model yet, built to run fast anywhere (CPUs, NPUs, and GPUs) to enable agentic ta…
Liquid AI releases LFM2.5-230M, a small 230M parameter model optimized for fast inference on CPUs, NPUs, and GPUs, targeting agentic tasks on devices like phones and robots.