kimi-k3-in-c.git
kimi-k3-in-c.git is A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. - FareedKhan-dev/kimi-k3-in-c. It is ranked #342 on the AI Radar, in Open & local models, first seen 7 h ago and shared in 2 posts (9.4k views).
GitHub - FareedKhan-dev/kimi-k3-in-c: A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation kimi-k3-in-c Public Notifications You must be signed in to change notification settings Fork 1.7k ( 1.7k )…
What people said about kimi-k3-in-c.git on X
💥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…
— @NFT_Chen, 7 h ago · 61 likes · see the post
😨惊了！Kimi K3.1 Pro + Cerebras 直接把浏览器代理玩成开挂模式！ 一条提示词，在 Best Buy 完整买下 LG 45寸 5K OLED 显示器： 找货 → 加购 → 结账 → 订单确认，全程 11.5 秒 推理速度最高冲到 2000 tokens/s，实测过程中实时跑到 2300+ 这种速度下，复杂 Browser Use 已经不是“能用”，而是“完全变态” 明年所有人都会想要这种速度的模型。Agent 真正起飞的时代来了。 #KimiK31Pro #Cerebras #AIAgent #BrowserUse #MoonshotAI #推理速度 #月之暗面…
— @NFT_Chen, 4 h ago · 16 likes · see the post
Alternatives to kimi-k3-in-c.git
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
- niklaslenz.com — Every number, the exact command and the raw output
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- project-maya — Plus a round of fixes, UI improvements and community PRs.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
kimi-k3-in-c.git in numbers
- Rank on the AI Radar: #342 of 10548
- Shared in 2 posts by 1 account: @NFT_Chen
- 9.4k views on those posts
- First seen 7 h ago, last shared 4 h ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is kimi-k3-in-c.git?
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. - FareedKhan-dev/kimi-k3-in-c It was first shared on X 7 h ago and is ranked #342 on the AI Radar.
Is kimi-k3-in-c.git free?
It is open source.
Who shared kimi-k3-in-c.git?
1 account on X, including @NFT_Chen, in 2 posts totalling 9.4k 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. 65.2k posts from 5k X accounts over the last 14 days, 10.5k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:40 UTC. Full method.