← News
Arena

A four-5080 Flash-Next report: 448.60 tok/s needs power and output conditions

A QEngine 1.3.5.9 community report states power caps, host offload and whole-reply timing limits. Weight quantization is not explicit in the retrieved report, so no benchmark row is imported.

Source: club-3090 社区报告及维护者修正

At 12:20 UTC on November 14, 2026, club-3090 issue #2033 published a four-RTX-5080 Qwen3.8-Flash-Next report generated at 11:22:11 UTC, within this observation window. QEngine 1.3.5.9, build ee98bd1, reportedly achieved mean decode rates of 448.60 tok/s for code and 366.93 for narrative over five measured runs per shape. This is one contributor's report, not an AraoAI reproduction.

Four cards alone do not identify the configuration. They use PCIe Gen5 x8 through a switch without NVLink. GPU0 is capped at 252W and the others at 250W. Experts are partly backed by host memory; MTP and n-gram lookup are enabled, and KV uses fp8_e4m3. These conditions prevent direct ranking against stock-power, all-VRAM or non-speculative configurations. A host-backing amount is not a measured VRAM footprint.

Addressable context is not recall quality. The configured context is 1048576, but boundary probes, stress checks, soak runs and ability tasks answer different questions. Separate thinking-on and thinking-off quality runs retain sampling=server stamps. A maintainer confirms that a later sampling-stamp fix cannot retroactively verify the old runs. Their scores do not establish a controlled causal benefit from thinking mode.

All twelve tool replies in the agentic run arrived in one output chunk. The reported first-chunk time therefore includes generation of the entire reply. Subsequent PR #2035 removes prompt-read growth grades for these cases while preserving measurements. Do not interpret the curve as prompt processing alone or infer decode from transmission gaps.

AraoAI retains the source and its missing fields rather than forcing a benchmark import. The retrieved issue and full comments do not explicitly state weight quantization. KV precision and attachment filenames cannot fill that field. A comparison starts with complete, auditable conditions.

Source: https://github.com/noonghunna/club-3090/issues/2033 Timing correction: https://github.com/noonghunna/club-3090/pull/2035