MiniMax M2
228.7B total, 11B active · 192k context · modified-mit · released 2025-10-22
codingagenticreasoningchat
What to run it on in the US
Fully in memory at 128k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
MoE model with 230B total / 10B active parameters; day-0 support in SGLang and vLLM, plus MLX and Transformers guides. Interleaved thinking model: prior <think>...</think> content must be kept in chat history or performance degrades.
Questions
- What licence is MiniMax M2 released under?
- modified-mit.