community-verified · measured pool data
Can the RTX PRO 6000 Blackwell Workstation Edition 96GB run Qwen3.5-122B-A10B-REAP-20?
Yes — community-measured at 126.5 tok/s (5 runs at 4-bit).
Verified single-stream runs on the RTX PRO 6000 Blackwell Workstation Edition 96GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.
| Quantization | Median tok/s | TTFT (ms) | Peak VRAM | Max context tested | Engines |
|---|---|---|---|---|---|
| 4-bit | 126.5 | 10165.7 | 83.7 GB | 65,536 | llama.cpp, vllm |