community pool / model answer
MiniMax-M2.7-AWQ-4bit
chat · cyankiwi/MiniMax-M2.7-AWQ-4bit
27.3 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 128GB | 4-bit | 27 tok/s | measured | 132 | - GB | 196,608 | 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.