MiniMax-M1 vs LLMs-from-scratch
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| MiniMax-M1 | LLMs-from-scratch | |
|---|---|---|
| Tagline | MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 3.2k | 99k |
| Forks | 283 | 15k |
| Open issues | 30 | 4 |
| Language | Python | Jupyter Notebook |
| License | Apache-2.0 | Other |
| Last pushed | Jul 7, 2025 | Jun 2, 2026 |
| Categories | LLM Frameworks | Model Training, LLM Frameworks |
MiniMax-M1
MiniMax-M1 is an innovative large-scale hybrid-attention reasoning model designed to advance the capabilities of language models and AI agents. It is released in an effort to contribute to the open-source community by providing a robust foundation for research and development in natural language understanding, reasoning, and general machine learning tasks.
Python
LLMs-from-scratch
Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.
Jupyter Notebook