Have you thought about getting a second 128GB device? Open weights models are rapidly increasing in size, unfortunately.
For now I will just wait for AMD or Intel to release a x86 platform with 256G of unified memory, which would allow me to run larger models and stick to Linux as the inference platform.
Unfortunately, AMD dumped a great device with unfinished software stack, and the community is rolling with it, compared to the DGX Spark, which I think is more cluster friendly.