Qwen3.6-35B-A3B decode ~3x slower than published benchmarks on Ryzen AI 7 350 / Ubuntu 24.04 — NPU validates at full 51 TOPS

Qwen3.6-35B-A3B decode ~3x slower than published benchmarks on Ryzen AI 7 350 / Ubuntu 24.04 — NPU validates at full 51 TOPS

Summary

On a Ryzen AI 7 350 (Krackan Point) running Ubuntu 24.04 with FLM v0.9.45, flm bench qwen3.6-moe:35b-a3b produces decode speeds roughly 1/3 of the numbers published on the Qwen3.6 benchmark page, which lists the same CPU, the same FLM version (v0.9.45), and the same default Performance power mode.

The same gap appears with gpt-oss:20b (~2x). Prefill is much closer to spec (~1.4x off), while decode is 2-3x off.

xrt-smi validate reports the NPU running at full spec (gemm TOPS: 51.0, PASSED), so the hardware itself appears healthy.

My main question: were the published benchmarks measured on Windows or Linux? The benchmark pages don't state the OS. If they're Windows numbers, this is a platform gap and my results may be expected on Linux. If they're Linux numbers, something else is going on.

Environment

Questions

1. Were the published benchmark numbers measured on Windows or Linux? The benchmark pages list CPU, RAM, and FLM version but not the OS. Given FLM's Linux support landed 2026-03-11, a Windows/Linux gap would explain this.
2. If they were measured on Linux, is there any additional configuration required beyond what I have above?
3. Is the corrupted output at 16k/32k a known issue?

Happy to run any additional diagnostics. Thanks for the great work on FLM.

Start by reproducing flm bench qwen3.6-moe:35b-a3b and gpt-oss:20b in the reported Ubuntu 24.04 environment, then compare the results with the published benchmark conditions. Use xrt-smi validate and the supplied configuration as reference; the investigation is done when the Windows/Linux status, any required configuration, and the 16k/32k output behavior are explained.