community-verified · measured pool data
Can the RTX 5090 32GB run Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP?
Yes — community-measured at 97.5 tok/s (5 runs at 4-bit).
Verified single-stream runs on the RTX 5090 32GB 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 | 97.5 | 115 | 32 GB | 131,072 | vllm |