💥疯了！2.78万亿参数的Kimi K3，仅需8.24GB内存就能在普通电脑上本地跑通！
This is a AI post classified by AGK Intelligence as Open & local models (a tool drop), kept by the AI Radar because it carries real work, not commentary.
💥疯了！2.78万亿参数的Kimi K3，仅需8.24GB内存就能在普通电脑上本地跑通！ 纯C99引擎，无GPU、无BLAS、无任何重框架，176KB二进制，MoE架构+磁盘流式加载，让万亿级模型真正“民主化”，普通笔记本也能跑完整模型，输出与官方一致！ 核心亮点 🔹峰值内存仅8.24GB（laptop预设），磁盘需约1.56TB权重 🔹纯CPU推理，支持Linux/macOS/Windows • 内存越大越快：8GB约26-33s/token，128GB+可到5.6s/token 🔹输出字节级一致，更多内存只换速度不换答案 📌 关键上手步骤 1️⃣克隆仓库：git clone https://github.com/FareedKhan-dev/kimi-k3-in-c.git && cd kimi-k3-in-c 2️⃣检查环境：./scripts/k3-doctor.sh（自动检测CPU/内存/磁盘） 3️⃣编译测试：make -j && make test（无需模型，1分钟内完成） 4️⃣下载模型（需HF Token）：export HF_TOKEN=你的token && ./scripts/download-model.sh ~/k3model 5️⃣打包主干：./scripts/pack-trunk.sh ~/k3model ~/k3trunk 6️⃣
Posted by SuSu_酥酥👅 (27.1k followers) 7 h ago · 86 likes · 11.8k views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: kimi-k3-in-c.git, kimi-k3-in-c, Try NVIDIA NIM APIs.
More AI work like this
- Qwen3.8 27B QSAではこのアーキテクチャを使い、速度低下を大幅に軽減しています — @_ryu15_
- Meet Mistral Small 3.2 24B Instruct, now in a heretic GGUF edition. This uncensored,… — @HuggingModels
- 💥细节感拉满！Qwen 4.0 蜜蜂向日葵测试炸了！ — @NFT_Chen
- @TheZachMueller — @TheZachMueller
- Here DSv4.1 Flash recipe by @christopherowen in action! — @ivanfioravanti
- Qwen Qoduck 花了 2 个小时生成的美国白宫 3D 建模 — @leo114119
- HyperFlow H3 Flash has passed 15,000 downloads on @huggingface in under 24 hours. — @video_rebirth
- Every lab should ship its own 4bit weights. — @plotarmordev
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. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:45 UTC. Full method.