Run a tiny local AI that generates short stories or text completions entirely offline, without Python or any AI framework installed.
Learn how large language model inference works at a low level by reading and modifying a single readable C file.
Train a small custom language model from scratch using the included PyTorch code, then run it with the C inference engine.
| karpathy/llama2.c | ish-app/ish | awesome-harmonyos/harmonyos | |
|---|---|---|---|
| Stars | 19,500 | 19,847 | 19,874 |
| Language | C | C | C |
| Setup difficulty | moderate | hard | easy |
| Complexity | 3/5 | 5/5 | 1/5 |
| Audience | researcher | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Needs a C compiler for inference, PyTorch is required only if training custom models from scratch.
llama2.c is a minimalist project that lets you run Llama 2, Meta's large language model AI, using a single file of plain C code with no external dependencies. The problem it solves is making AI language models approachable for learning and experimentation: instead of a huge complex codebase, you get one readable 700-line file that handles the inference (the "run the AI" part), plus PyTorch code for training smaller versions from scratch. The way it works is that you either download one of the pre-trained "TinyLlamas" (small models trained on short stories, ranging from 15M to 110M parameters) or export Meta's official Llama 2 weights into the project's format. You then compile and run the C file, which reads the model and generates text. It runs surprisingly fast, around 110 tokens per second on an M1 MacBook Air for the small models. You can give it a text prompt and it will continue the story or answer in kind. You'd use this if you want to understand how AI language models work at a low level, run a tiny AI locally without Python or heavy frameworks, or just experiment with text generation for educational purposes. The tech stack is C for inference, Python and PyTorch for training.
llama2.c runs Meta's Llama 2 AI language model using a single 700-line C file with zero dependencies, ideal for learning how AI inference works or running a tiny local text generator without Python.
Mainly C. The stack also includes C, Python, PyTorch.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly researcher.
This repo across BitVibe Labs
Verify against the repo before relying on details.