running-qwen3-8-flash-next-on-dgx-spark-and-rtx-pro-6000

[giscus[bot]]

running-qwen3-8-flash-next-on-dgx-spark-and-rtx-pro-6000

Qwen dropped Qwen3.8-Flash-Next this week, and the first thing I saw on my timeline was somebody saying it will not fit on a single DGX Spark. The NVFP4…

https://blog.kubesimplify.com/running-qwen3-8-flash-next-on-dgx-spark-and-rtx-pro-6000

[laurentperez]

Hi. Great article, very useful information.
Nvidia recently released https://huggingface.co/nvidia/Qwen3-Next-80B-A3B-Instruct-NVFP4.
The RadixArk you listed fails to run inference, but did you try the nvidia one ?
Thanks