Every vendor benchmark with an 'X times faster' number hides one question you need to ask before you believe it: faster than what. On 10 July AMD published results on its blog for the MI350X accelerator in image generation. At first glance it sounds strong. Up close, the number answers a completely different question.
Fact
The facts, by AMD's numbers: FLUX.1-dev generates an image 2.25x faster (6.22 versus 14.02 seconds); Z-Image-Turbo generates 6.29x faster (1.76 versus 11.07 seconds); Qwen-Image-Edit-2511 edits an image 5.78x faster (21.89 versus 126.52 seconds). Conditions: one accelerator, one request at a time, bfloat16, 1024 by 1024 pixels. The baseline is the unoptimized reference implementation HuggingFace Diffusers, not a previous-generation AMD chip and not an NVIDIA chip. The tests were run and published by AMD employees, with no independent third-party verification.
I'll believe it when I see how the MI350X holds up against an NVIDIA chip, on the same software. That's exactly the comparison that's missing. AMD is measuring its own optimized software against a baseline implementation nobody runs in production in that shape. The 6x answers how much AMD gains from its own optimization - not whether it's faster than the competition.
AMD is comparing itself to itself. That's not a lie. But it's not the answer either.
Don't read this as proof the MI350X beats NVIDIA - the post doesn't claim that, and we shouldn't put words in its mouth. The more important signal is that AMD is putting serious work into the software layer, and that's exactly where it's been weak for years. Its hardware hasn't been the problem for a while now. Whether this turns into an advantage will show up in independent tests down the line.
Official primary sources
AMD ROCm BlogThe visual is generated code-art, no third-party images.