🔥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！
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
🔥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 + 全局注意力），边缘设备速度和内存都更优 手机上手步骤： 1️⃣下载 GGUF：https://huggingface.co/AtomicChat/LFM3-1.7B-Uncensored-GGUF（推荐 AD-Q4_K_M） 2️⃣安装支持 GGUF 的手机 App（PocketPal AI / 类似本地推理 App，或 Termux + llama.cpp） 3️⃣导入模型文件，设置温度 0.1、top-k 50、repeat penalty 1.1 4️⃣直接开聊，全程离线、隐私拉满，还能玩 Agent 任务 官方权重和更多模态版本在 LiquidAI Huggi
Posted by SuSu_酥酥👅 (24.6k followers) 2 days ago · 104 likes · 6.7k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: lfm3-1.7b-uncensored-gguf, liquidai.
More dev work like this
- 长PDF要是拆成单页再往一块拼，跨页表格和阅读顺序十有八九会乱套，这事你八成也烦过。 — @bkdgiffug
- Local models on Apple Silicon finally feel like a product, not a weekend project. — @PixelRainbowNFT
- GPT 6.1 Terra max vs GPT 6.1 Sol max — @HarshithLucky3
- Asked at the Meetup: "Does sbx run mistral work?" — @ajeetsraina
- Most agents freeze once deployed. — @GoogleCloudTech
- Your $250 GPU can now run a 35B coding model at 50 tokens/sec. — @0x0SojalSec
- Next week we're showing how to build self improving products. — @spenserskates
- Seedance 2.5 US Draft mode is now available on fal — @fal
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 22:12 UTC. Full method.