community pool / model answer
MiniMax-M2.7
chat · MiniMaxAI/MiniMax-M2.7
32.2 tok/s · model median · 34 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B70 32GB ×4 | 4-bit | 37.7 tok/s | measured | - | 29.2 GB | 24,576 | llama.cpp, vllm |
| GB10 Grace Blackwell 128GB | 4-bit | 30.9 tok/s | reported | 807 | 117 GB | 108,000 | llama.cpp |
| Radeon AI Pro R9700 32GB ×3 | 4-bit | 25.2 tok/s | measured | 771 | - GB | 32,768 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.