Comment by walrus01
15 hours ago
It's not that GLM5.3 in full precision unquantized is any smaller, it's 141 * 5.4GB files at approx 770GB which is about the same size as 5.2.
15 hours ago
It's not that GLM5.3 in full precision unquantized is any smaller, it's 141 * 5.4GB files at approx 770GB which is about the same size as 5.2.
Hold on.. the routed experts are in FP8 now? Previously they were in BF16. Nice, this shall cut my download time by half!
This time they just made FP8 "default", accompanied by "-BF16" model/page (previously "-FP8" was released alongside).