I’d recommend trying LM Studio (https://lmstudio.ai/). You can use it to run language models locally. It has a pretty nice UI and it’s fairly easy to use.
I will say, though, that it sounds like you want to feed perhaps a large number of tokens into the model, which will require a model made for a large context length and may require a pretty beefy machine.
Several years ago, I contracted for a short time as a software engineer for a team within Walmart that was working on an in-house digital label solution. It was pretty cool as it was all custom hardware running Android. I think the project probably could’ve been run better, though. I’d guess that’s part of the reason they have taken so long to deploy some type of digital label solution, and ultimately went with a third party product.