Gemma3n as a daily driver sounds nice—4b or 8b? and rough tokens/sec on your laptop? And have you A/B‑tested code generation quality across local models (e.g., Gemma3n vs others)?
I am using the smaller one, specifically the e2b-it flavor.
I get ~20-30 tok/sec. It's fast enough that its not frustrating, but if it were faster you could more easily skim as it generates.
I haven't done any serious testing. My process is typically learning about new models on HN or elsewhere, and trying to give them a real shake. I have some goto code generation prompts that I try on all of them. None succeed but they are getting close. I also do a lot of just feeling it out. The more I can use solutions unedited the better it feels.
I get ~20-30 tok/sec. It's fast enough that its not frustrating, but if it were faster you could more easily skim as it generates.
I haven't done any serious testing. My process is typically learning about new models on HN or elsewhere, and trying to give them a real shake. I have some goto code generation prompts that I try on all of them. None succeed but they are getting close. I also do a lot of just feeling it out. The more I can use solutions unedited the better it feels.