MiniMax M1 40k
456.1B total, 48.4B active · 1024k context · Apache License 2.0 · released 2025-06-05
chatcodingagenticreasoning
What to run it on in the UK
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
456B-total / 45.9B-active hybrid MoE with lightning attention, released in 40K and 80K thinking-budget variants. vLLM is recommended for production serving; Transformers is also supported.
Questions
- What licence is MiniMax M1 40k released under?
- Apache License 2.0, which allows commercial use.