r0b0tlab

/

nex-n2-mini-nvfp4

like 5

Thanks for putting this together. Could you please provide some guidance on how to run this on a single node GB10 (DGX Spark) device? I’m currently serving vLLM using Docker and have tried a few configurations borrowed from Qwen3.6-moe, but they don’t seem to work. Any assistance you can provide would be greatly appreciated!