MindStudio tested an MSI Prestige N16 Flip AI+ powered by Nvidia's RTX Spark platform and found that AI performance dropped by nearly 80% when running Linux while plugged in. Running OpenAI's GPT-OSS-120B model, the laptop generated 65.4 tokens per second on Windows, but only 13.9 tokens per second on Linux with the charger connected — a nearly 79% reduction. Unplugging the laptop brought much of that performance back. The gap appeared in other tests too: Windows completed one AI workload in roughly eight minutes, while Linux took 37 minutes. MindStudio considered overheating but found temperatures stayed between 40 and 47 degrees Celsius; instead, the GPU ran at much lower clock speeds under Linux — approximately 2.2 GHz on Windows versus around 780 MHz on Linux while plugged in. The researchers traced the problem to an Nvidia component called Platform Controllers and Framework, which manages power distribution between CPU and GPU on Windows but lacks equivalent Linux support for the system tested. Disabling the controller in Windows immediately dropped performance and GPU clock speeds to approximately the same levels seen under Linux, while restoring it brought performance back. The team also reported that the firmware's power-management information is encrypted, preventing Linux from accessing the needed settings. The MSI laptop supports up to 128GB of unified memory.