#56 · Primary category： Foundation Models
MiniMax-M2
MiniMax-M2, a model built for Max coding & agentic workflows.
Project last updated：11/13/25
GitHub Stars
2.6K
Forks
215
Contributors
5
License
Other
Why we included this project
MiniMax-M2 is an open-weight model that aims to give you strong coding and agent behavior without paying for a much larger system. It's a sparse mixture-of-experts design: 230 billion total parameters, but only 10 billion are active for each forward pass. That sparsity is what keeps it practical on modest hardware, and on coding benchmarks it competes with much bigger commercial models, handling multi-file edits, run-and-fix loops, and terminal-driven repairs. If you're building a coding assistant or an autonomous agent and would rather self-host than call a big API, this is a serious option. The MIT license and released weights on Hugging Face and ModelScope make integration and fine-tuning straightforward.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities