AI-Hypercomputer/maxtext
A simple, performant and scalable Jax LLM!
MaxText helps AI engineers and researchers efficiently train and fine-tune large language models (LLMs) on powerful hardware like Google Cloud TPUs and GPUs. You provide raw text data and choose from a library of existing model architectures like Gemma or Llama. MaxText then outputs a highly optimized, custom-trained LLM ready for integration into your applications or further research.
2,169 stars. Actively maintained with 321 commits in the last 30 days. Available on PyPI.
Use this if you need to pre-train or fine-tune large language models from scratch or adapt existing ones for specific tasks, aiming for high performance and scalability on accelerator hardware.
Not ideal if you're looking for an off-the-shelf API for LLM inference or if you don't have access to specialized AI accelerator hardware for training.
Stars
2,169
Forks
485
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
321
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/AI-Hypercomputer/maxtext"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related models
rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
mindspore-lab/mindnlp
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless...
mosaicml/llm-foundry
LLM training code for Databricks foundation models
rickiepark/llm-from-scratch
<밑바닥부터 만들면서 공부하는 LLM>(길벗, 2025)의 코드 저장소
CASE-Lab-UMD/LLM-Drop
The official implementation of the paper "Uncovering the Redundancy in Transformers via a...