{"slug": "nvidia-s-spark-laptop-runs-linux-at-one-third-speed", "title": "Nvidia's Spark laptop runs Linux at one third speed", "summary": "Nvidia's RTX Spark laptop throttles its GPU to about 780 MHz under native Linux versus 2.2GHz on Windows, cutting GPT-OSS-120B inference to 13.9 tokens per second on Linux against 65.4 on Windows, 65.1 in WSL and 61 on the DGX Spark desktop, according to a MindStudio analysis. The cause is Nvidia's Windows-only \"Nvidia Platform Controllers and Framework\" driver, which manages CPU-GPU power splitting; the firmware table governing GPU power states is encrypted and only the Windows driver holds the key. MindStudio reproduced the Linux figure on Windows by disabling the controller, with throughput falling from about 83 tokens per second to 32 and clocks from 2GHz to 786MHz, while the unthrottled DGX Spark desktop is unaffected.", "body_md": "Nvidia’s Spark laptop runs Linux at one third speed\n\nInstall Linux on an RTX Spark laptop, plug it in, and the GPU locks to about 780 MHz. The same chip hits 2.2GHz on Windows. On GPT-OSS-120B that is 13.9 tokens per second on native Linux against 65.4 on Windows, 65.1 in WSL and 61 on the DGX Spark desktop. Identical hardware, roughly five times the throughput, decided entirely by which operating system boots.\n\nThe cause is a Windows-only component Nvidia ships as “Nvidia Platform Controllers and Framework”, a hidden device in Windows Device Manager that manages how power is split between CPU and GPU on these machines. Linux has no equivalent driver. The firmware table that governs GPU power states is encrypted, and only the Windows driver holds the key.\n\n## The experiment that proves it\n\nThe MindStudio analysis did the thing that makes a claim into a finding: it disabled the controller on Windows and re-ran the benchmark. Throughput fell from about 83 tokens per second to 32, and clocks fell from 2GHz to 786MHz. That is the Linux number, reproduced on Windows by removing the one driver Linux never had.\n\nThere is a twist that makes it worse for anyone planning a dual boot. On battery power, Linux wins, reaching about 61 tokens per second unplugged. Plug the charger in and it becomes the slowest configuration tested. The machine is fastest on battery and slowest on wall power, which is the opposite of how every laptop on earth behaves.\n\n## The memory split is a second, quieter problem\n\nThe laptop reserves 96GB of unified memory for the GPU by default, and only Windows exposes a setting to change that split. On Linux the machine inherits whatever the firmware decided, which means before you can even benchmark the GPU you may find the CPU side has almost nothing to work with. WSL sidesteps the clock problem because it rides on the Windows driver, but it defaults to 14GB of memory and needs manual tuning.\n\n## What it means for the Spark thesis\n\nThis site has recommended DGX Spark hardware as a way to get CUDA-native inference in a small box, including a three-Spark cluster build. That recommendation was about the desktop unit, and the desktop unit is not throttled, hitting 61 tokens per second in the same test. The laptop is the different product with the different problem.\n\nIf your plan is a Spark laptop as a portable local AI machine, run Windows, or run WSL with the memory split tuned by hand. If your plan is a Spark desktop or a cluster, nothing in this changes it.\n\n## Why this matters beyond one laptop\n\nThe pattern is bigger than Nvidia. As local AI moves onto systems with unified memory and shared power budgets, the operating system becomes part of the performance specification. Firmware that only one OS can configure turns “Linux support” into a checkbox that is technically true and practically useless.\n\nThat matters for anyone buying hardware on the assumption that Linux is the safe choice for a local inference box. On this machine it is the slow choice, by a factor of five, and the reason lives in an encrypted table no open driver can read.", "url": "https://wpnews.pro/news/nvidia-s-spark-laptop-runs-linux-at-one-third-speed", "canonical_source": "https://tokenstead.ai/guides/rtx-spark-linux-throttle", "published_at": "2026-11-05 12:35:45+00:00", "updated_at": "2026-11-05 12:54:45.330950+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-chips", "ai-tools"], "entities": ["Nvidia", "RTX Spark", "DGX Spark", "MindStudio", "GPT-OSS-120B", "Windows", "Linux", "WSL"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/nvidia-s-spark-laptop-runs-linux-at-one-third-speed", "markdown": "https://wpnews.pro/news/nvidia-s-spark-laptop-runs-linux-at-one-third-speed.md", "text": "https://wpnews.pro/news/nvidia-s-spark-laptop-runs-linux-at-one-third-speed.txt", "jsonld": "https://wpnews.pro/news/nvidia-s-spark-laptop-runs-linux-at-one-third-speed.jsonld"}}