News for hackers. Stuff that matters.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by muyuu on Sunday March 01, 2026 @02:12AM (#47204425)
Depending on the specificity of the research, having a model with fewer parameters will come with a higher penalty. If you want a model to perform better at something specific while staying smaller, generally it will take specific training to achieve that.

There are no comments on this comment yet.