unknown

Super in-depth guide setting up Qwen3.5-122B-A10B on 2 x 128GB M4 Max Mac Studios from scratch w/ @exolabs.

Total cost $8k. Runs at 52 tok/sec.

Imagine M5 Max mac mini. The amount of edge compute accessible to consumers will be huge: ~27.5% more memory bandwidth &amp; ~4x FLOPS. https://t.co/XwwCFN0n2J https://t.co/Fbs6hRLkmJ

Alex Finn

A bold prediction claims that within 3 months, a Mac Mini will be capable of running a frontier AI model on par with Claude Opus locally, enabling fully private, zero-cost, unlimited AI inference for autonomous business building.

Imagine this world:

Mac Mini on your desk. Runs a frontier model just as good as Opus locally

100% private. 0 cost.

Unlimited superintelligence building you a business 24/7. Earning you $

We are literally 3 months away from this and basically nobody is talking about it. Why? https://t.co/U82IRrAP5S

<p>Imagine this world:

Mac Mini on your desk. Runs a frontier model just as good as Opus locally

100% private. 0 cost.

Unlimited superintelligence building you a business 24/7. Earning you $

We are literally 3 months away from this and basically nobody is talking about it. Why? https://t.co/U82IRrAP5S</p>