community pool / model answer
Qwen3.5-122B-A10B-REAP-20
chat · 0xSero/Qwen3.5-122B-A10B-REAP-20
126.5 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX PRO 6000 Blackwell Workstation Edition 96GB | 4-bit | 126.5 tok/s | measured | 10,166 | 83.7 GB | 65,536 | llama.cpp, 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.