
MiniMax-M1
by MiniMax-AI (organization)
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. (description from the project’s GitHub page)
Repository facts
- Stars
- 3,185
- Forks
- 285
- Open issues and pull requests
- 33
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- MiniMax-AI · Organization
- Created
- Jun 14, 2025
- Last push
- Jul 7, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 1,483: rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
5,425 starsJupyter NotebookApache-2.0Last push Oct 2, 2026
Rank 8,416: HKUDS/LightReasoner
[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
611 starsPythonMITLast push May 22, 2026
Rank 978: zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
8,342 starsPythonApache-2.0Last push Sep 22, 2026
Rank 64: hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
75,561 starsPythonApache-2.0Last push Oct 10, 2026
Rank 138: ray-project/ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
44,061 starsPythonApache-2.0Last push Oct 18, 2026
Rank 157: HKUDS/LightRAG
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
40,199 starsPythonMITLast push Oct 15, 2026