That’s exactly what I mean. It all depends on what makes a company big tech.
If it’s just having lots of money or capital then it’s really hard to divest oneself because of the phenomenal heights of industry required to make chips. Like, on some level you gotta accept that no one’s doing 14nm lithography in a shed out behind their house (people who do home lithography are in the micrometer range last I looked).
You can always just use an m series mac if you don’t want to support Intel or amd.
It all depends on how you define big tech.
The framework risc v board, for example, uses the StarFive JH-7110 which is manufactured by tsmc. Doesn’t get much bigger than that!
Specs for what?
The hardware you run it on will have a range of specs.
The model you try to use will have a bunch of measurements that can be called specs.
Once you pick some hardware, the measurements of the model you run on it can be adjusted for “accuracy” or speed.
Of course, the range of hardware that’s available to you informs that calculus.
The alternative to answering this post is to get a Mac mini or whatever they’re selling as a desktop llm device now and not mess around.
It depends on what they want. The op and title are pretty vague and general, so I offered a very easy solution that could meet their needs.