community pool / model answer
Qwen3.5-122B-A10B-GPTQ-Int4
chat · Qwen/Qwen3.5-122B-A10B-GPTQ-Int4
49.1 tok/s · model median · 1 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB ×8 | 4-bit | 49.1 tok/s | reported | 177 | 170.4 GB | 8,192 | 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.