🚨炸了！Liquid AI 发布 LFM3：2B 小模型性能直接对标甚至超越 6 倍以上更大模型！
This is a dev post classified by AGK Intelligence as Other (a launch), kept by the Dev Radar because it carries real work, not commentary.
🚨炸了！Liquid AI 发布 LFM3：2B 小模型性能直接对标甚至超越 6 倍以上更大模型！ LFM3-VL-2B（仅 1.9B 参数）在视觉基准上与 Gemma 4 12B 打平，并与 Gemini 3.5 Flash Lite、GPT-5.6 Luna 同级；文本版则在端侧智能帕累托前沿登顶，同时支持 256K 超长上下文。 核心亮点： 🔹全新 Tri-Hybrid 架构：门控短卷积 + 滑动窗口注意力 + 全局注意力，参数更少、能力更强 🔹全模态家族：文本、视觉语言、音频、Omni、决策模型，共 6 款约 2B 参数模型 🔹真正端侧友好：针对 14 类硬件优化，4-bit 约 1GB，单 GPU 即可微调，支持本地私有部署 🔹开源即用：权重已上 Hugging Face，同步开放 Playground 与 API 端侧专业智能，真的来了。 官方博客：https://www.liquid.ai/blog/lfm3 权重：https://huggingface.co/collections/LiquidAI/lfm3 #LiquidAI #LFM3 #端侧AI #开源AI #多模态 #小模型大能力 #OnDeviceAI
Posted by SuSu_酥酥👅 (24.5k followers) 3 days ago · 342 likes · 25.5k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: liquidai.
More dev work like this
- took @rehan_shei's open-source pixel fx into a real 3D scene and made the wizard… — @majidmanzarpour
- 彭博终端贵得让个人用户直摇头，这感受你应该不陌生。 — @bkdgiffug
- I went quiet for a few weeks because what I’m building now is better than every library… — @dwhitedesign
- Celestia’s Voyager handled 21M transactions per second in its first big test — @BSCNews
- Our annual kiroween hackathon is here, and submissions are officially open. 🎃 — @kirodotdev
- Em paralelo ao projeto do Launcher de Colin McRae (que tá funcionando bonitinho,… — @AkitaOnRails
- 😱炸了！智谱Zai创始人唐杰在清华课堂硬核算账：大模型尽头是算账！揭秘GLM系列模型跑在纯国产芯片是怎么“玩得起”的？！ — @NFT_Chen
- Ano passado brinquei de 4K upscaling com Real ERSGAN. Bom ver o claudinho automatizando… — @AkitaOnRails
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.