MiniMax-M1-40k
MiniMax-M1-40k is an open-weights language model from MiniMax, released June 13, 2025. It has 456B parameters (mixture-of-experts, 48B active). The context window is 10.2M tokens.
We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism.
Check it against your own PC →
Can you run MiniMax-M1-40k locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Benchmark results
Epoch AI has not published results for MiniMax-M1-40k yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: MiniMaxAI/MiniMax-M1-40k
More from MiniMax
MiniMax-M3.1-Flash · MiniMax-M3 · MiniMax-M2.7 · MiniMax-M2.5 · MiniMax-M2.1 · MiniMax-M2 · MiniMax-M1-80k