LOCAL models. No one is running Kimi 2.5 on their Macbook or RTX 4090.

Some people spend $50k on a new car, others spend it on running Kimi K2.5 at good speeds locally.

No one's running Sonnet/Gemini/GPT-5 locally though.

On Macbooks, no. But there are a few lunatics like this guy:

https://www.youtube.com/watch?v=bFgTxr5yst0

Wow!

I've never heard of this guy before, but I see he's got 5M YouTube subscribers, which I guess is the clout you need to have Apple loan (I assume) you $50K worth of Mac Studios!

I'll be interesting to see how model sizes, capability, and local compute prices evolve.

A bit off topic, but I was in best buy the other day and was shocked to see 65" TVs selling for $300 ... I can remember the first large flat screen TVs (plasma?) selling for 100x that ($30K) when they first came out.

He must be mad, accepting $50k of free (probably loaned?) hardware from Apple !

Great demo video though. Nice to see some benchmarks of Exo with this cluster across various models.