[suheilaaita]

The simplest way to really start, use anything like claude code, vs code, cursor, antigratvity, (or any other IDE) ask them to install ollama and pull the latest solid local model that was released that you can run based on your computer specs.

Wait 5-10 minutes, and should be done.

It genuinely is that simple.

You can even use local models using claude code or codex infrastrucutre (MASSIVE UNLOCK), but you need solid GPU(s) to run decent models. So that's the downside.

[cloogshicer]

Genuine question, will this actually give you the latest solid local model?

I would've thought no, because of the knowledge cutoff in whatever model you use to download it.

[suheilaaita]

I think it will give you a good "starter model". But then, it ultimately depends on what you want to do with the model exactly and your computer's specs.

For example, I needed a local model to review some transactions and output structured output in .json format. Not all local models are necesserily good at structured outputs, so I asked grok (becuase it has solid web search and is up to date), what are the best recommended models given this use case and my laptop's specs. It suggested a few models, I chose one and went for it and now it's working.

To summarise, - find model given use case and specs. - trial and error - test other models (if needed) - rinse repeat - because models are always coming out and getting better

[jiggunjer]

What knowledge cutoff? They all have web agents to Google it.

[suheilaaita]

They all do, true. But some are better than the others in how they retrieve, digest and present you with the information. Boils down to personal preferences and experimenting.