community pool / model answer
Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16
chat · SergiioB/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16
107.8 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B70 32GB | 4-bit | 80.6 tok/s | measured | 266 | - GB | 131,072 | 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.