M4 macs are becoming an interesting (and surprisingly cheaper) option for running local LLMs. They have lots of unified memory, integrated gpus and neural cores that are pretty good for running local models.

https://youtu.be/GBR6pHZ68Ho

Reply to this note

Please Login to reply.

Discussion

What models are you running? Am building my own machine running running local LLMs too (AMD/nVidia based).

Just took delivery of an Asus GeForce 12GB 3060. Not sure if I’ll swap it with my daughters 3070 yet :-)

You use Hugging Face to try them out?

Not sure what this means

Its a repository for different models

My son is looking at M4 Mac .. is it worth the price .. he is an AI dev ..

Yes. The base model M4 Mac Mini is one of the best deals on any computer right now.

Yeah, I just saw that video too, even just the new base model Mac mini looks great for a local LLM at your house - plus it doesn't actually use much power somehow (thanks Apple Silicon lol).

I'm most amazed by what my phone can do locally, and what my mom's lower RAM/weaker CPU phone can do locally

Inference is getting more memory efficient over time, and device memory is getting bigger. Exciting times.

I've ran the numbers running my local LLM with this and its really hard to beat with a custom built PC

Just upgrade hardware in 24 mo. and you'll stay at a reasonable "bleeding edge" of local LLM bare metal

It's quite difficult to beat $799 for such a dominant mini PC (24 GB Ram)

I yolo bought a 64gb model, going to use it as my backup bitcoin node + large model inference tasks

Brilliant🚀

M4 Pro is still a great deal if you want to swing the ~2M sats

Just realized you can get an m4 macbook with 128gb of unified ram. That would be wild for large model inference. A little more pricey but… hmm

70B LLM's would be easy to run...👀

🤔

Yeah you get 8tokens a second though

True

Need to max out the cores. Idk if a 14-core CPU is enough

A single core CPU is enough tbh

Surely there's more you could be doing to increase the attack surface

Minisforum EM780 is cheaper, 32GB RAM, and actually mini by modern standards (small enough to fit in a pocket)

Care to share link?

Looks like the official store is one of the only places that's not saying it's sold out right now

https://store.minisforum.com/products/minisforum-em780

might as well build a cluster