News for hackers. Stuff that matters.

A comment on Compress any LLM 3x in one click,near-lossless,in under 50 MB RAM.

Re:Compress any LLM 3x in one click,near-lossless,in under 5... by Roark66 on Tuesday November 10, 2026 @10:35AM (#50441854)
Hmm, this claims "functionally lossless" compression over 3x. But where is the starting point? Bf16 of fp16? If so, how much better is it than current quantization techniques?

This should be tested on a medium size dense model. For example Qwen3.8-27B. How much better is it t than quantization to 4.5 bits?

[ Parent | on HN ]

There are no comments on this comment yet.