Peasant Smith
@PeasantSmith
Old grumpy IT guy pushing AI onto old hardware.
Project Maya - Run GLM 5.3 Flash today on the hardware you own ๐ซก
๊ฐ์
August 2026
442 ํ๋ก์ ์ค 819 ํฌ
GLM 5.3 Flash on a single 3090 at 24.3 t/s decode and over 1000t/s prefill ๐ฅ
And yes, prefill has been optimised and it does get faster the bigger the context window, not magic, just hard work on Maya engine ๐ซก
๋ ๋ณด๊ธฐ
