kimi-k3-in-c
kimi-k3-in-c 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 #524 on the AI Radar, in Open & local models, first seen 45 days ago and shared in 1 post (80.3k 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 Appearance settings 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…
What people said about kimi-k3-in-c on X
🤯 震惊，kimi-k3-in-c 居然能让一台没显卡的普通电脑，跑起 2.78 万亿参数的 Kimi K3 大模型。 kimi-k3-in-c 在 GitHub 三个月狂揽 1 万多 star，已经有人把它移植到 Mac、改写成 Rust、补上 Metal 后端，围着它长出一片周边。 以前想在本地碰一个顶配大模型，门槛是几块专业显卡加一柜子显存，个人根本玩不起。它用纯 C99 把整套推理重写了一遍，不依赖 BLAS、不依赖任何深度学习框架，编译出来的引擎才 176KB。 办法是把权重边读边算：稠密主干和专家分开流式加载，笔记本档位实测峰值内存压到 8.24GB，一台 16G…
— @Ryrenz, 23 h ago · 32 likes · see the post
Alternatives to kimi-k3-in-c
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- niklaslenz.com — Play the world in your browser. 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.
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
kimi-k3-in-c in numbers
- Rank on the AI Radar: #524 of 10402
- Shared in 1 post by 1 account: @Ryrenz
- 80.3k views on those posts
- First seen 45 days ago, last shared 23 h ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is 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. - FareedKhan-dev/kimi-k3-in-c It was first shared on X 45 days ago and is ranked #524 on the AI Radar.
Is kimi-k3-in-c free?
It is open source.
Who shared kimi-k3-in-c?
1 account on X, including @Ryrenz, in 1 post totalling 80.3k 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. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.