FYI, Qwen3.8-Flash-Next-NVFP4 works quite well on a single DGX Spark (GB10)!

#53
by donghwan-shin - opened

Thanks to SGLang's recipe: https://docs.sglang.io/cookbook/autoregressive/Qwen/Qwen3.8-Flash-Next#hw=dgx-spark&variant=default&quant=nvfp4-nvda&strategy=low-latency&nodes=single&pleOffload=file

You can run Qwen3.8-Flash-Next-NVFP4 on a single DGX Spark (GB10) at a reasonable speed. I am using it now, and it was worth upgrading from Qwen3.8-27B-NVFP4.

what tok/sec?

I'm also using it on a single spark, I reduced also the speed to 50% to avoid getting too hot as I just keep it working while I do other stuff, I don't mind waiting for the final response, for me it's 25-30 tps.

I'm also using it on a single spark, I reduced also the speed to 50% to avoid getting too hot as I just keep it working while I do other stuff, I don't mind waiting for the final response, for me it's 25-30 tps.

DGX spark runs that hot?? My 5070 ti, ran the model at 20tps but 70C under load.

DGX spark runs that hot?? My 5070 ti, ran the model at 20tps but 70C under load.

My Spark has been working all day, and right now it's at 55-65 °C. Before I added the speed cap, it was getting really hot, I could burn my finger just touching it. Not anymore. 😁

Sign up or log in to comment