Smaller models are great if you are doing targeted changes in existing codebases. Don’t expect to use it for creating complex architecture from scratch or do major refactors. The larger the context, the greater the drop off will be.
Smaller models are also excellent executors/operators. When given a solid plan, including e.g. what files/functions to change and how, what to test, even a recent 27-30B open weight model will usually do an excellent job.