AITOPAI热报
ModelsSelected

Liquid AI 发布开源权重模型 LFM3，1.7B 版本超越自家 2.6B 前代

rohanpaul_ai@rohanpaul_ai
Post
View the post
Why we picked it

小模型逆袭的典型案例：Liquid AI 的 1.7B 开源模型靠混合架构干掉了自家 2.6B 老版本，跑智能体任务还大幅超过 Qwen3.5-9B。

Liquid AI 推出开源权重模型家族 LFM3，其中 1.7B 文本模型在成绩上超过了 2.6B 的上一代。性能提升来自三混合架构：24 层中 13 层用短卷积、5 层用 256-token 滑动窗口注意力、6 层做全局注意力。在 Liquid 自测的智能体基准 AutomationBench 上，LFM3 1.7B 拿到 41.29 分，而 Qwen3.5-9B 只有 15.10 分。

Original · rohanpaul_ai

Liquid AI just launched LFM3, an open-weight model family whose 1.7B text model beats its 2.6B predecessor.

The gain comes from a tri-hybrid design: of 24 layers, 13 are short convolutions, 5 use 256-token sliding-window attention and 6 attend globally.

That efficiency carries into agent benchmarks run by Liquid, where the 1.7B model scores 41.29 on AutomationBench while Qwen3.5-9B manages 15.10.

#Liquid AI#LFM3#Qwen3.5#开源模型#推理模型

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-sourceSelected19:14
Liquid AI releases d1-ultra, topping Artificial Analysis Decision Index

The trade-off here is deliberate: Liquid AI swapped raw accuracy for knowing when not to answer, which matters more for agentic decision workflows where a wrong answer is costlier than a refusal. Builders routing high-volume decisions can compare it directly against Celeris-1 Decision ($32 per 1M tasks), Mercury Decide ($15) and GPT-6 Luna (Decisions) ($79) on both price and speed.

#Liquid AI#d1-ultra#decision models#benchmarks
Event
官方账号Artificial Analysis@ArtificialAnlys3 sourcesSource
ModelsUS vs ChinaSelected15:09
Liquid AI releases LFM2.5-24B-A2B for local agents

A sparse mixture-of-experts design that keeps only 2B parameters active per token lets a 24B model run locally while matching a larger dense-activation rival on tool-use work, changing what is practical on consumer hardware. Developers building local agent workflows can pull it with a single Ollama command or grab the open weights on Hugging Face to fine-tune. Compared with Qwen3.6-35B-A3B, it targets the same agentic niche at lower active-parameter cost.

#Liquid AI#LFM2.5#Ollama#open-source models
ollama@ollamaSource