community pool / model answer
Qwen3.5-9B-AWQ-4bit
chat · cyankiwi/Qwen3.5-9B-AWQ-4bit
68.4 tok/s · model median · 9 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 4-bit | 79.1 tok/s | measured | 6,060 | 19.6 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.