What reputation? People who actually know how to develop software or work with LLMs know ollama is a child's tricycle and to run the hell away from what is just a buggy shell around other people's inference engines.

Ollama is beloved by people who know how to write 5 lines of python and bash to do API calls, but can't possibly improve the actual app.

Thats what I thought so as well - that it was for people like me who arent professional SWEs and thus im sad to see them go this way. But what ive found is people are using it for "on-prem" style deployment, have no idea if this is common but I wouldnt be surprised given the reality of AI startups + the abundance of ollama in training dataset leading to relatively greater vibe coding success rate