[Ignore my earlier caution about the NVIDIA image — I raised a concern about kernel module flavors upstream and it was disproven on real hardware: `-nvidia` OS images ship the proprietary NVIDIA kernel module flavor — Blackwell GPUs (GB10 / DGX Spark, RTX 50-series) cannot initialize · Issue #3465 · Start9Labs/start-technologies · GitHub]
Definitive answer, confirmed by Start9’s CTO who runs StartOS on this exact hardware: StartOS beta.9 aarch64-nvidia on a DGX Spark works, GPU acceleration functional. So:
- Take a full backup.
- Flash the
aarch64-nvidiaISO (published alongside the standard image for every release) and keep your existing data drive when the installer offers. - Don’t skip the MOK step. If Secure Boot is enabled, the setup wizard walks you through enrolling the StartOS signing key — a blue MokManager screen appears on reboot and you have about 10 seconds to choose “Enroll MOK” (it reappears on every boot until enrolled). Without it the NVIDIA module can’t load and you’d see exactly the CPU-only behavior you reported.
- Verify with
nvidia-smiover SSH on the host; Ollama’s startup log should then report a CUDA backend instead oflibrary=cpu.
Would love to see tokens/sec once it’s running — and let us know how it goes.