nanochat
nanochat is The best ChatGPT that $100 can buy. Contribute to karpathy/nanochat development by creating an account on GitHub.. It is ranked #560 on the AI Radar, in Open & local models, first seen 10 days ago and shared in 3 posts (185.5k views).
GitHub - karpathy/nanochat: The best ChatGPT that $100 can buy. · 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 nanochat Public Notifications You must be signed in to change notification settings Fork 8.3k ( 8.3k ) Star 59k ( 59k ) You must be signed in to star a repository About The best ChatGPT that…
What people said about nanochat on X
holy f*ck, Karpathy put an entire AI degree on GitHub for free 7 repos, 306,741 stars, and in the right order they take you from backprop to agents that run research overnight each repo is the next layer of the one before 1. micrograd -> how a neural net actually learns backprop in about 100 lines of Python ↳…
— @Mr_Buzzoni, 10 days ago · 3.7k likes · see the post
holy f*ck, Karpathy put an entire AI degree on GitHub for free 7 repos, 306,741 stars -> in the right order they take you from backprop to agents that research overnight every repo builds on the one before it 1. micrograd -> how a neural net learns backprop in about 100 lines of Python ↳…
— @Mr_Buzzoni, 3 days ago · 122 likes · see the post
🔮 又挖到一个宝藏：Karpathy 的 nanochat，48 美元、两小时就能自己训出一个 GPT-2 水平的模型。 nanochat 在 GitHub 已经 5.9 万 star，作者是 OpenAI 联合创始人 Andrej Karpathy。 2019 年训 GPT-2 大约要花 43000 美元，按文档的说法，现在在一台 8 卡 H100 节点上跑参考脚本，约 2 小时、约 48 美元就能达到同样的能力。 想搞懂大模型是怎么从零训出来的，以前得在一堆框架和配置里来回翻。nanochat 把分词、预训练、微调、评估、推理整条链路塞进一个读得懂、改得动的精简代码库，模型大小只看一个 --depth…
— @Ryrenz, 4 days ago · 28 likes · see the post
Alternatives to nanochat
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
- 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.
nanochat in numbers
- Rank on the AI Radar: #560 of 10410
- Shared in 3 posts by 2 accounts: @Mr_Buzzoni, @Ryrenz
- 185.5k views on those posts
- First seen 10 days ago, last shared 3 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is nanochat?
The best ChatGPT that $100 can buy. Contribute to karpathy/nanochat development by creating an account on GitHub. It was first shared on X 10 days ago and is ranked #560 on the AI Radar.
Is nanochat free?
It is open source.
Who shared nanochat?
2 accounts on X, including @Mr_Buzzoni, @Ryrenz, in 3 posts totalling 185.5k 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 16:05 UTC. Full method.