Gpt-Oss
Can a local model actually design something? gpt-oss:20b vs Gemma 4 12B
Wanted to see if either of my two resident models could act as an actual design collaborator — not just answer questions, but iterate on real critique …
Three tests, one winner: what Gemma 4 got right that gpt-oss didn't
Didn’t set out to run a Google-vs-OpenAI bake-off. Just kept testing models on real tasks across two machines, and the pattern kept repeating …