Hacker News Reader

> It's better than the benchmark scores seem to indicate compared to Qwen 3.6 27B. I'm very excited for 3.8

Is it worth considering if it's only marginally better than Qwen 3.6 though? Qwen 3.8 27B is almost there, and will probably be better suited as drop-in replacement for 3.6. Not even considering there's probably going to be a 3.8-35B-A3B too - which will have even better performance.

View on HN

Qwen3.6 is very token inefficient with it's thinking. Quantized versions often get into loops.

Glimmer is trained with 4 effort levels, not just thinking on/off. Maybe it's more token efficient in general. There's official 4 bit quantizations with reported 1% loss across 15 benchmarks -- so quants probably work good.

IMO that alone is worth trying for, even if they're otherwise equal.

It takes 10 minutes to download and try, any model is worth at least that. In my experience benchmarks are generally dogshit

Reply on news.ycombinator.com