What GPU do you need to run MiniMax M2.5?
228.7B params 192K max context ReasoningTool use
The smallest GPU memory that runs MiniMax M2.5 well is 192 GB (Q4_K_M, e.g. Ryzen AI Max 400 (Gorgon Halo)). 4 of 132 GPUs run it well.
MMLU 82 SWE-bench Verified 80.2
VRAM needed per quantization
| Quantization | Weights | 16K context | 32K context | Full 192K |
|---|---|---|---|---|
| Q4_K_M | 128.8 GB | 132.6 GB | 136.4 GB | 174.3 GB |
| Q8_0 | 226.4 GB | 230.2 GB | 234.0 GB | 271.9 GB |
Weights plus fp16 KV cache. Leave ~1 GB headroom for the inference engine.
GPUs that can run MiniMax M2.5
Best quantization that fits on each GPU, with the context and speed it gets. For chips with several memory sizes, the smallest that works is shown.
AMD
- Ryzen AI Max 400 (Gorgon Halo) 192 GB Q4_K_M 192K context · ~2 tok/s