Dev Radar
Support
LiveUpdated 2026-10-30 20:27 UTC

liquidai

liquidai — Collection of base and post-trained LFM3 models (www.liquid.ai/blog/lfm3).

liquidai is Collection of base and post-trained LFM3 models (www.liquid.ai/blog/lfm3).. It is ranked #245 on the Dev Radar, in Other, first seen 3 days ago and shared in 2 posts (32.2k views).

Visit huggingface.co

💧 LFM3 - a LiquidAI Collection Hugging Face Log In Sign Up LiquidAI 's Collections 💧 LFM3 💧 LFM2.5 🎯 Liquid Nanos 🇯🇵 LFM JP 👁️ LFM2.5-VL 🔈 LFM2.5-Audio 💧 LFM2 👁️ LFM2-VL 🔈 LFM2-Audio 🧪 Liquid Longevity LLMs 💧 LFM3 updated 1 minute ago Collection of base and post-trained LFM3 models (www.liquid.ai/blog/lfm3). Upvote 30 +20 Sort: Collection LiquidAI/LFM3-1.7B Text Generation • 2B • Updated about 12 hours ago • 6.31k • 50 LiquidAI/LFM3-VL-2B Image-Text-to-Text • 2B • Updated about 2 hours ago • 255 • 26 LiquidAI/LFM3-Audio-2B Any-to-Any • 2B • Updated about 2 hours ago • 156 • 22 LiquidAI/LFM3-Omni-2B Any-to-Any • 2B • Updated…

What people said about liquidai on X

🚨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…

— @NFT_Chen, 3 days ago · 342 likes · see the post

🔥炸了!手机上就能玩转 Liquid AI 最新 LFM3-1.7B Uncensored 模型,1.7B 参数硬刚 9-10B 模型,还完全本地运行! 关键亮点: 🔹AtomicChat 的 Uncensored GGUF:拒绝率从 61.7% 直接干到 0%,MMLU 等指标几乎零损失 🔹4-bit 量化仅约 1.1GB,轻松塞进手机 🔹256K 超长上下文 + 原生工具调用,专为本地 Agent 优化 🔹官方 LFM3 家族还有 Vision / Audio / Omni / Decision 模型,全在 2B 级,可单卡微调、端侧部署 🔹架构是 tri-hybrid(短卷积 + 滑动窗口注意力 +…

— @NFT_Chen, 2 days ago · 104 likes · see the post

Alternatives to liquidai

liquidai in numbers

FAQ

What is liquidai?

Collection of base and post-trained LFM3 models (www.liquid.ai/blog/lfm3). It was first shared on X 3 days ago and is ranked #245 on the Dev Radar.

Is liquidai free?

It is open source.

Who shared liquidai?

1 account on X, including @NFT_Chen, in 2 posts totalling 32.2k views.

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.