Alex Ziskind
@digitalix
Software engineer making videos about dev gear, local AI, and weird tech experiments
๊ฐ์
March 2009
1.5K ํ๋ก์ ์ค 27.5K ํฌ
Faster chips, new bottleneck ๐คฏ
Two clustered M5 Ultra Macs ran SLOWER than one: 35 tok/s vs 53. Which is strange, considering my experiments with M3 Ultra were the opposite.
Keep the GPUs awake and they jump to 58 tok/s.
๋ ๋ณด๊ธฐ
