I feel the primary benefit of this Ollama Turbo is that you can quickly test and run different models in the cloud that you could run locally if you had the correct hardware.

This allows you to try out some open models and better assess if you could buy a dgx box or Mac Studio with a lot of unified memory and build out what you want to do locally without actually investing in very expensive hardware.

Certain applications require good privacy control and on-prem and local are something certain financial/medical/law developers want. This allows you to build something and test it on non-private data and then drop in real local hardware later in the process.

I'm not sure the major models will remain at $20. Regardless, I support any and all efforts to keep the space crowded and competitive.

Running models without a filter on it. OpenAI has an overzealous filter and won’t even tell you what you violated. So you have to do a dance with prompts to see if it’s copyright, trademark or whatever. Recently it just refused to answer my questions and said it wasn’t true that a civil servant would get fired for releasing a report per their job duties. Another dance sending it links to stories that it was true so it could answer my question. I want a LLMs without training wheels.

I think its the data privacy is the main point and probably more usage before you hit limits? But mainly data privacy i guess

I run a lot of mundane jobs that work fine with less capable models, so I can see the potential benefit. It all depends on the limits though.

Groq seems to do okay with a similar service but I think their pricing is probably better.

Privacy, I guess. But at this point it’s just believing that they won’t log your data.

nothing lmao. this is just ollama trying to make money.