[lrvick]

As another data point.

Running Qwen3.5 122B at 35t/s as a daily driver using Vulcan llama.cpp on kernel 7.0.0rc5 on a Framework Desktop board (Strix Halo 128).

Also a pair of AMD AI Pro r9700 cards as my workhorses for zimageturbo, qwen tts/asr and other accessory functions and experiments.

Finally have a Radeon 6900 XT running qwen3.5 32B at 60+t/s for a fast all arounder.

If I buy anything nvidia it will be only for compatibility testing. AMD hardware is 100% the best option now for cost, freedom, and security for home users.

[plagiarist]

How is the performance for Z-Image on the R9700s?

[lrvick]

About 10 seconds for a 1024x1024 on one, but not found a nice way to scale processing a single image across both.

[syntaxing]

Are the dedicated GPU cards on another machine or you’re using eGPU with the framework?

[lrvick]

A separate machine.