Reasoning

MiniMax M2 Non-Commercial License (modified MIT base)Open weightsUpdated June 2026Legacy baseline

MiniMax M2

The first release in MiniMax's M2 line: a 228.7B-parameter sparse mixture-of-experts model (8 experts active per token) with a 196,608-token context window -- a major efficiency step down from the 456B M1 generation.

MiniMax · MiniMax

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesMiniMaxAI/MiniMax-M2 on Hugging Face

Model checkpoints, context windows, provider support, local runtime compatibility, and license terms can change quickly. Verify the exact model card before production or commercial use.

Best for

Builders who want the baseline M2-generation release for comparison against later M2.x point releases or M3.

Who should use it

Builders who want the baseline M2-generation release for comparison against later M2.x point releases or M3.
Teams with access to hosted inference or server-class deployment paths.
Developers evaluating coding assistant, repo-editing, and code review workflows.
Teams testing tool-use, agentic planning, and multi-step workflow behavior.

Common workflows

Coding, reasoning, tool use, office workflows, agents
reasoning workflows
coding workflows
tool-use workflows
agents workflows

Deployment and hardware notes

228.7B total parameters, 8 experts active per token. No GGUF in the official repository -- server-class multi-GPU or hosted inference only.

License and usage notes

MiniMax M2 Non-Commercial License (modified MIT base). Open weights. Verify the exact model card and license terms for the checkpoint or hosted provider you use.

Strengths

Open weights model option for MiniMax workflows.
Builders who want the baseline M2-generation release for comparison against later M2.x point releases or M3.
Tracked as Legacy baseline in the OpenSourcesAI model directory.

Limitations

Same non-commercial licensing terms as the rest of the M2 line: prior written authorization required for commercial use. No official or community GGUF -- server-class or hosted inference only. Superseded by M2.1, M2.5, and M2.7 for production use.
228.7B total parameters, 8 experts active per token. No GGUF in the official repository -- server-class multi-GPU or hosted inference only.
Context window and limits: 196,608 tokens, confirmed from the model's published config.
Verify the exact model card, provider docs, license, and serving support before production use.