community pool / model answer
MiniMax-M2.7-int4-AutoRound
chat · Lasimeri/MiniMax-M2.7-int4-AutoRound
61.3 tok/s · model median · 58 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 | 61.3 tok/s | measured | 23,336 | 28.1 GB | 32,768 | vllm |
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.