@Meta Open architecture. Leadership performance.
AMD Helios delivers up to 30% more tokens/$ on leading AI models.
And, AMD Helios delivers leadership throughput on DeepSeekR1, with 17,000 tokens/second/GPU.
AMD Helios claims up to 30% more tokens per dollar on AI models
AISummary
AMD says its Helios platform delivers up to 30% more tokens per dollar on leading AI models. AMD also reports 17,000 tokens per second per GPU on DeepSeek-R1, which it describes as leadership throughput.
Post on XView on X
Source: AMD · x.comPublished · added here