Hello,
I'm really interested about the new Ryzen AI 370 HX processor and have been following the announcements about its AI capabilities (using NPU and/or iGPU). The initial reviews look promising, but I've noticed something missing that I'm really curious about. I am working on some research projects and we plan to run some LLMs on "edge" devices like those processors.
While there's been talk about AI performance, I haven't seen any benchmarks for large language models like Llama 3 8B on this processor. Some competitors, like the Snapdragon X Elite, have already shared this kind of information (via QC AI HUB for example).
I'm wondering if anyone has insights or if there are plans to release benchmarks for LLM inference on the Ryzen AI 370 HX (or a similar chip)?
This would be super helpful for understanding how it performs with these increasingly important AI workloads.
Thanks in advance for any info you can share!
