community-verified · measured pool data
Can the RTX 5090 32GB ×2 run Qwen3.6-27B-Text-NVFP4-MTP?
Yes — community-measured at 85.3 tok/s (2 runs at 4-bit).
Verified single-stream runs on the RTX 5090 32GB ×2 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 | 85.3 | 2752.4 | 59.3 GB | 262,144 | vllm |