I think the bigger bottleneck is SLAM, running that is intensive, it wont directly run on video, and SLAM is tough i guess, reading the repo doesn’t give any clues of it being able to run on CPU inference.

There is a repo they released.

It will, they have released a repo with code.

I am not a bot trust me.

taste of his own medicine

I checked mostly all of em out from the list, but 1b models are generally unusable for RAG.

i use pageassist with Ollama

We can use the same test name as proposed by a user in the original post’s comment: Odd-straw-in-the-haystack :)