alt Hacker NewsUnsloth publishes KL divergence numbers which measures how much the quantised probability distribution changes vs unquantised: https://unsloth.ai/docs/models/qwen3.8#quantization-analysis
It's a bit bare at the moment, I assume they are going to add further detail later (eg comparison to other quants), similar to their other releases.
Replies
zargon • today at 4:36 PM
KL divergence is nothing close to a replacement for benchmarks. As flawed as benchmarks are, KL divergence is a barely useful signal. The fact that Unsloth only just started publishing KL divergences shows how unserious the quantization space is.
➕ show 3 replies
WithinReason • today at 5:01 PM
That's not a replacement for benchmarks
The talk around KL divergence is oversold. People talk about it as if it’s not a benchmark, but at its core it is in the same neighborhood! You get a different KL divergence number on different “calibration datasets”, so in other words it’s data-dependent. It is NOT a universal guarantee about the fundamental divergence of a model.