🤯天呐！Pi 和 Claude Code 用户狂喜！工具Token调用狂砍 40%！LiquidAI LFM2.5-24B-A2B + HF 专属 LoRA 适配器来了！
This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
🤯天呐！Pi 和 Claude Code 用户狂喜！工具Token调用狂砍 40%！LiquidAI LFM2.5-24B-A2B + HF 专属 LoRA 适配器来了！ 24B 总参数，仅 2B 激活的 MoE 端侧 Agent 模型，先思考再行动 + 131K 上下文，配上针对开源框架调优的适配器，直接让 Pi / Claude Code 更聪明、更省成本、更可预测。 核心亮点： 🔹专为 Pi & Claude Code 打造的 LoRA，最高减少 40% 工具调用 🔹端侧私有运行，速度快、成本可控，企业级专业化智能 🔹先思考再调用工具，效率与质量双提升 快速上手 3 步： 1️⃣下载基座：https://huggingface.co/LiquidAI/LFM2.5-24B-A2B 2️⃣拉取适配器：https://huggingface.co/collections/harness-hub/lfm25-24b-harness-adapters 3️⃣加载 LoRA（支持 Transformers / llama.cpp / GGUF），接入本地 OpenAI 兼容端点后配置到 Pi 或 Claude Code 即可！ 现在就让你的 Agent 少绕弯路、多干正事 ！ 模型卡：https://huggingface.co/LiquidAI/LFM2.5-24B
Posted by SuSu_酥酥👅 (25k followers) 1 h ago · 16 likes · 891 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: lfm2.5-24b-a2b, harness-hub, 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 22:17 UTC. Full method.