We unlocked NVFP4 on the DGX Spark: 20% faster than AWQ!

[chrm]

Hello,

I am new to the DGX Spark (HP ZGX) platform and have been following the impressive results shared in this forum. It is great to see the progress achieved - well done to everyone involved.

I have not yet conducted any tests or benchmarks myself, but I am curious whether we can expect similar performance improvements on the DGX Spark as those described in NVIDIA’s announcement, “Announcing new VLLM container & 3.5X increase in Gen AI Performance in just 5 weeks of Jetson AGX Thor Launch.”

Announcing new VLLM container & 3.5X increase in Gen AI Performance in just 5 weeks of Jetson AGX Thor Launch

A key advantage of the NVIDIA software stack is its commitment to continuous improvement. Frequent software optimizations mean that existing models are consistently accelerated—delivering better performance with simple software updates. We’ve demonstrated this with Jetson platforms like Orin and Xavier, and are now showcasing these gains on Jetson AGX Thor. Just a few weeks after launch, we’ve boosted Gen AI performance on Jetson AGX Thor by up to 3.5X compared to our initial results we showcas…

Should we anticipate comparable gains on our DGX Spark systems? That would be truly remarkable.

Thank you in advance for your insights.