Remix.run Logo
oceanplexian 3 hours ago

Doing inference with a Mac Mini to save money is more or less holding it wrong. Of course if you buy some overpriced Apple hardware it’s going to take years to break even.

Buy a couple real GPUs and do tensor parallelism and concurrent batch requests with vllm and it becomes extremely cost competitive to run your own hardware.

mythz 3 hours ago | parent [-]

> Doing inference with a Mac Mini to save money is more or less holding it wrong.

No one's running these large models on a Mac Mini.

> Of course if you buy some overpriced Apple hardware it’s going to take years to break even.

Great, where can I find cheaper hardware that can run GLM 5's 745B or Kimi K2.5 1T models? Currently it requires 2x M3 Ultras (1TB VRAM) to run Kimi K2.5 at 24 tok/s [1] What are the better value alternatives?

[1] https://x.com/alexocheema/status/2016404573917683754