“Where are the engineers” to manage this on prem hardware?

Well, you laid them off, you fuck.

Of course IBM has a hardware solution for you

Krishna also predicted demand for on-prem AI will spur sales of Big Blue’s Spyre mainframe accelerator cards.

Guy selling fruit says fruit is juicy more breaking news at 11

I mean, obviously, but I guess the only reason they're saying this is because their own models aren't that great (IBM granite sucks) and this way they can still sell consulting services.

Whose premises? Release the GPUs and make them cheap again you motherfuckers

Maybe I'm just sleep deprived, cynical, or thinking too deep into it, but I don't even like how they are using the words "on-prem" throughout the article instead of simply saying they're running local LLMs. Seems like such a weird choice of wording that is meant to subtly steer less informed people away from looking into alternatives to the subscription based LLM services, as most casual people wont associate it as the same thing and ignore it and move on. Even if that's the correct terminology for that specific field, I feel like most people would just naturally say "Yes, we are running the LLM servers locally here" as that's the only way I've ever heard people say it even online.

BTW, IBM/RHEL is hoping you might go for some red hat, IBM solutions for local distributed AI stuff :

• https://www.redhat.com/en/artificial-intelligence/inference#distributed-inference
• https://developers.redhat.com/products/rhel-ai/overview
• https://www.redhat.com/en/products/ai/enterprise-linux-ai

But you know, the CEO isn't biased. /s

At least they're working on letting you have access to the open source (ish) local way of working with AIs instead of just the subscription model that the others are pushing.

I did some digging into this before giving the fuck up since my computer is a potato, and I have too many fucking things to do with my time.

It was always the future no big tech wanted.... That's why they enbeded models everywhere.

Man who has a vested interest in selling sever hardware: "You can buy a server and host things on-prem"

Pure big AI (OpenAI, Anthropic) companies are so cooked, small models are coming to eat their lunch. Meta, Google et.al. have other arrows in their quiver. Even IBM are likely too big, Qwen 3.8 27B is a beast you can host on a gaming rig and suitable for many, many use cases.