community pool / model answer
Qwen3.8-27B-GPTQ-INT8-W8A8-GS128
chat · curvedinf/Qwen3.8-27B-GPTQ-INT8-W8A8-GS128
132.4 tok/s · model median · 1 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Instinct MI100 32GB ×4 | 8-bit | 132.4 tok/s | reported | 28 | 128 GB | 64,000 | 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.