The easiest way to run an open model on your own machine: one command downloads and starts it, plus a local REST API and libraries for Python and JavaScript.
All repositories
Open models & inferencekarpathy
nanochat
Rookie of the month
The whole path from zero to your own ChatGPT-like chat in one repo: tokenizer, pretraining, fine-tuning and UI. Designed to train for roughly a hundred dollars.
Who it is for
For people who want to go through the full chat-model build cycle themselves on one GPU machine.
How to start
- Set up the environment:
uv sync --extra gpu(or--extra cpufor CPU and MPS). - Run the full pipeline:
bash runs/speedrun.sh(built for an 8xH100 node, about 1.5 hours). - Talk to your model:
python -m scripts.chat_cli.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+753Sep 6 — Oct 6
Author's description
The best ChatGPT that $100 can buy.
More in «Open models & inference»
The core library for working with models: one codebase for text, vision, audio and multimodal tasks, for both inference and training. Most new open models ship through it.
A self-hosted ChatGPT-style interface that connects to Ollama and any OpenAI-compatible API. Installs with a single Docker command and runs on your own server.
A C/C++ engine that runs language models on ordinary hardware: laptops, phones, GPU-less servers. Much of local AI, Ollama included, is built on it.
Repository of the large open DeepSeek-V3 mixture-of-experts model: description, benchmark results and run instructions. It showed an open model can stand next to closed ones.
The foundation under most modern neural networks: GPU-accelerated tensors and automatic differentiation, wrapped in ordinary Python. Transformers, Llama and nearly every open model are written on it.