LocalLLaMA

2739 readers

51 users here now

Welcome to LocalLLama! This is a community to discuss local large language models such as LLama, Deepseek, Mistral, and Qwen.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support eachother and share our enthusiasm in a positive constructive way.

founded 2 years ago

MODERATORS

SkySyrup@sh.itjust.works

pax@sh.itjust.works

noneabove1182@sh.itjust.works

Smokeydope@lemmy.world

MonsterBug@sh.itjust.works

Mac Studio 2025 (piefed.social)

submitted 2 weeks ago by Oskar@piefed.social to c/localllama@sh.itjust.works

6 comments fedilink hide all child comments

Thinking about a new Mac, my MPB M1 2020 16 GB can only handle about 8B models and is slow.

Since I looked it up I might as well shared the LLM-related specs:
Memory bandwidth
M4 Pro (Mac Mini): 273GB/s M4 Max (Mac Studio): 410 GB/s

Cores cpu / gpu
M4 pro 14 / 20
M4 Max 16 / 40

Cores & memory bandwidth is of course important, but with the Mini I could have 64 GB ram instead of 36 (within my budget that is fixed for tax reasons).

Feels like the Mini with more memory would be better. What do you think?

top 6 comments

sorted by: hot top controversial new old

[–] iStone@feddit.org 1 points 2 weeks ago (1 children)

Depends on what model you want to run?

[–] Oskar@piefed.social 1 points 2 weeks ago (1 children)

of course, I haven't looked at models >9B for now. So I have to decide if I want to run larger models quickly or even larger models quickly-but-not-as-quick-as-on-a- Mac-Studio.

Or I could just spend the money on API credits :D

[–] iStone@feddit.org 2 points 2 weeks ago

Use API credits. 64GB can barely run a 70B model. I have a MacBook Pro M3 Max with 128GB and can run those and even slightly bigger models. But results are underwhelming. Not bought for LLM only, but if I would have, I would be disappointed.

[–] papertowels@mander.xyz 1 points 2 weeks ago (1 children)

Have you considered the framework desktop? Uses amd strix halo. The same cost for the Mac mini (2k?) gets you around 90gb vram, out of a 128gb unified ram configuration.

[–] Oskar@piefed.social 1 points 2 weeks ago (1 children)

Interesting, lots of "bang for the buck". I'll check it out

[–] papertowels@mander.xyz 1 points 2 weeks ago

Yup! They even had a demo clustering 5 of them to run deep seek proper