Nvidia RTX Spark encrypted firmware slows inference speed to 35% on Linux
- ID
- 42998
- Status
- summarized
- Published
- 04 Nov 2026, 4:46 PM
- Fetched
- 05 Nov 2026, 12:01 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://www.mindstudio.ai/blog/linux-nvidia-rtx-spark-laptop
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.5
- Created
- 05 Nov 2026, 12:01 AM
- Tags
- Audience
- developersai_ml_learnersvibe_coders
What happened
A hands-on write-up of dual-booting Linux on the MSI Prestige N16 Flip AI Plus (Nvidia RTX Spark) found that Linux works — desktop, GPU acceleration via Nvidia's open kernel driver, 4K 120Hz, audio, touchpad — but the GPU locks to roughly 780 MHz when plugged in versus about 2.2 GHz on Windows. The cause is Nvidia's Platform Controllers and Framework, a Windows-only component whose power table is encrypted and unreadable by Linux. On GPT-OSS-120B the gap is stark: Windows 65.4 tokens/sec, WSL 65.1, DGX Spark 61, native Linux 13.9; a second blocker is that the laptop reserves 96GB of unified memory for the GPU by default and only Windows exposes the setting to change that split.
Why it matters
If you were planning to buy an RTX Spark laptop as a portable local-inference box for Linux, the measured numbers say don't run it bare-metal today: 13.9 vs 65.4 tokens/sec on GPT-OSS-120B is a ~4.7x penalty, and you also can't repartition the 96GB GPU memory reservation from Linux. The practical workaround is WSL, which rides the Windows driver stack, keeps full GPU boost on battery and wall power, and still runs Linux-first tooling like vLLM — so budget for Windows as the host OS until Nvidia ports the platform controller's power management into its Linux driver.
Discussion angle
Encrypted firmware power tables as a de-facto lock-out: is 'just use WSL' an acceptable answer for Linux-first AI developers, or does it make the open kernel driver claim hollow — and what would it take for Nvidia to commit to porting the platform controller logic?