Serving Deepseek v4 Flash 0731 on 2x DGX Spark — 5-7 GB OS headroom, what would you do to lower VRAM usage and increase OS available RAM?

Hey all, I'm serving DSv4Flash 0731 on a cluster of 2x DGX Sparks but am running into constant issues with having almost no RAM (unified memory) left for the OS/cache and I'd love to hear the community feedback on what I could do to get more RAM for headroom. The DGX has an issue where it locks up w