minGPT vs OpenMythos
Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.
Open source · MIT
A small, readable PyTorch re-implementation of GPT for training and running language models.
Open source · MIT
A community-written, theoretical PyTorch model of a looped transformer, inspired by speculation about Claude M
The short answer
Choose minGPT if you need…
- Students who want to read a working GPT implementation end to end
- Developers who want a small, hackable base for experimenting with transformer models
- People who want to load GPT-2 weights and generate text with PyTorch
- Researchers who prefer a minimal codebase over a large framework
Choose OpenMythos if you need…
- Researchers exploring looped or recurrent-depth transformer designs
- Developers who want a small, readable PyTorch codebase to experiment with MLA or GQA attention
- Students studying how sparse mixture-of-experts and loop-based depth fit together
- People who want to test compute-adaptive reasoning ideas at small scale
Side-by-side
| minGPT | OpenMythos | |
|---|---|---|
| Type | Library | Library |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 25k | 14.9k |
| Setup difficulty | Intermediate | Intermediate |
| How you get it | Clone and build from source | Install with a package manager |
| Main language | Python | Python |
| Last code update | 2 years ago | 6 months ago |
What each one is
minGPT
minGPT is a compact PyTorch codebase that reimplements the GPT transformer model, covering both training and inference. The README describes it as roughly 300 lines of model code, split into a model file, a byte pair encoder, and a generic training loop, aimed at being easy to read and learn from. It is a library you import into your own Python project, with demos for tasks like addition and character-level text generation.
OpenMythos
OpenMythos is a Python library that implements a Recurrent-Depth (looped) Transformer in PyTorch. Instead of stacking many unique layers, a middle block of layers is reused several times per forward pass, with the input re-injected each loop. The project states it is an independent, theoretical reconstruction based on public research and speculation, and is not affiliated with Anthropic.
Best for
minGPT
- Students who want to read a working GPT implementation end to end
- Developers who want a small, hackable base for experimenting with transformer models
- People who want to load GPT-2 weights and generate text with PyTorch
- Researchers who prefer a minimal codebase over a large framework
OpenMythos
- Researchers exploring looped or recurrent-depth transformer designs
- Developers who want a small, readable PyTorch codebase to experiment with MLA or GQA attention
- Students studying how sparse mixture-of-experts and loop-based depth fit together
- People who want to test compute-adaptive reasoning ideas at small scale
Strengths
minGPT
- Small enough to read in an afternoon, with the model in about 300 lines according to the README
- Clear separation between model, tokenizer, and training loop
- MIT licensed and widely referenced in notebooks, blogs, and courses
OpenMythos
- Small, documented API with a clear usage example in the README
- Supports two attention types (MLA and GQA) switchable through one config field
- Released under the MIT license, permitting reuse
Not ideal for
minGPT
- People who need an actively maintained project: the README says minGPT is in a semi-archived state and points to nanoGPT for newer work
- Anyone needing distributed training or mixed precision, which the README lists as todos
- Users looking for a ready-made chatbot or polished end-user app
OpenMythos
- Anyone expecting a working replica of Anthropic's Claude models, since the README says it is speculative and unaffiliated
- People looking for a ready-to-use chat assistant, as the README shows only small example configs and no trained model
- Users without a CUDA GPU who need the Flash Attention path, since the README says it requires CUDA and build tools
Trade-offs
minGPT
- Semi-archived as of January 2023; the author suggests nanoGPT for newer development
- Test coverage is described as limited, and there is no requirements.txt yet per the README
- Lacks mixed precision and distributed training, which are listed as future todos
OpenMythos
- The README describes the work as theoretical and speculative, so claims about Claude Mythos are unverified
- The README lists pre-configured scales up to 1T parameters, but the example model code and the variant table do not show trained weights or benchmark results
- The usage example calls mythos_7b() although the listed variants do not include a 7b entry, so the README is internally inconsistent
Getting started
minGPT
Clone the repository
git clone https://github.com/karpathy/minGPT.gitEnter the directory
cd minGPTOpenMythos
Install from PyPI
pip install open-mythosInstall with uv
uv pip install open-mythosFrequently asked questions
What is the difference between minGPT and OpenMythos?
minGPT: A small, readable PyTorch re-implementation of GPT for training and running language models. OpenMythos: A community-written, theoretical PyTorch model of a looped transformer, inspired by speculation about Claude M. minGPT suits students who want to read a working gpt implementation end to end, while OpenMythos suits researchers exploring looped or recurrent-depth transformer designs.
Are minGPT and OpenMythos free?
minGPT: Free and open source. OpenMythos: Free and open source.
Is minGPT or OpenMythos more popular?
minGPT has more GitHub stars (25k) than OpenMythos (14.9k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to minGPT and OpenMythos?
Other options people compare them with include llm.c, FightingCV, FastAPI-MCP.
Keep comparing
Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.