Dual RTX 3090 report: 220 W caps are part of the result
A community report documents dual RTX 3090 inference with QEngine 1.3.2, explicit power caps and phase-specific measurements. It remains L0 self-reported evidence, not independent AraoAI replication.
Two reports labeled “dual 3090” need not describe comparable configurations. A new club-3090 issue #1897 documents Qwen3.8-27B INT4 on QEngine 1.3.2 with two RTX 3090 cards capped at 220 W each, NVLink, and Ubuntu 24.04.5 LTS. The report was generated on October 31 at 17:51 UTC, inside this window. Every measurement below is the author's self-report, not an independent AraoAI reproduction.
-
Read conditions first. The report records driver 615.71.10, FP8 KV, a 262144-token serving limit, sampling settings and negotiated PCIe Gen4 x8 links. A 220 W cap is neither measured average power nor the card's rated TDP. NVLink presence does not establish which transport every execution phase uses.
-
Keep phases separate. At the 10K-input phase, three samples give mean prefill of 2363.43 tok/s and same-phase decode of 106.44 tok/s. At the 90K phase, one sample gives 1920.08 and 117.68 tok/s respectively. Both phases allow only 16 output tokens; these are short depth probes, not long-response steady-state rates. Narrative and code prompts are different phases and must not be spliced into a universal result.
-
Preserve limitations. MTP-related draft configuration invalidates the ordinary one-dense-pass bandwidth bound. Some motherboard and memory details were not collected without root. Missing measurements must not be inferred from another post, nominal card capacity or engine allocation targets.
This report supplies traceable reproduction conditions, not a GPU ranking. AraoAI treats it as L0 evidence; record imports remain drafts pending review. QEngine carries a noncommercial license, so availability is not commercial authorization.
Source: https://github.com/noonghunna/club-3090/issues/1897 License: https://github.com/bpx03/QEngine/blob/main/LICENSE