@leto_bao: Mac Studio has gotta be the most worthwhile thing I bought this year... The MacBook M2 Pro 32GB I got back when I was w…
Summary
A user shares how upgrading from an M2 Pro MacBook to a 128GB Mac Studio lets them run around a dozen Claude coding sessions concurrently, noting the machine is a worthwhile buy for heavy AI workloads and that they won't return to a MacBook Pro for heavy lifting.
View Cached Full Text
Cached at: 10/05/26, 03:35 PM
Mac Studio has gotta be the most worthwhile thing I bought this year…
The MacBook M2 Pro 32GB I got back when I was working could only handle one thing at a time—either coding, or running quant backtests, or checking stocks, or watching YouTube. Trying to juggle a few tasks would make it freeze up, but back then, it was enough for me since I had no energy left after work to mess around with anything else.
But now that I’m not working and tinkering with stuff at home every day, my energy outstrips my computing power. Upgraded to the M5 Max 128GB, and now I can run a dozen or so Claude sessions at once while watching YouTube on the side without breaking a sweat—memory usage usually hits about 90GB, which is just right. Though honestly, that’s also the limit of my own focus; any more sessions and I just can’t keep up.
I probably won’t buy another MacBook Pro in this lifetime. For heavy lifting, you should just get a Mac Studio. When I’m out and about, I’ll use the iPad or MacBook Neo to remote connect and get work done.
Similar Articles
Apple Mac Studio (M5 Ultra) Review: Unlimited Power
Wired reviews Apple's Mac Studio with the M5 Ultra chip, highlighting its ability to run frontier-level AI language models locally with up to 256GB of unified memory, while noting it still lags behind Nvidia GPUs and can run hot.
Apple introduces new Mac Studio with M5 Max and M5 Ultra - up to 512GB of unified memory
Apple has introduced the new Mac Studio with M5 Max and M5 Ultra chips, offering up to 4.3x faster AI performance and 512GB of unified memory for on-device AI and pro workflows.
@Michaelzsguo: So you bought the 128GB MacBook Pro. Now the question is not, “Which local model gets the highest TPS?” It is: which se…
This thread recommends a local AI coding stack for the 128GB MacBook Pro, using Qwen 3.6 model with MLX server and specific configurations for reliable coding assistance.
Is it worth getting 128GB MacBook Pro? Will it ever be comparable to today’s frontier models for coding?
A developer questions whether a high-RAM MacBook Pro for local AI models could match cloud frontier models like Claude for coding, considering long-term costs.
2x 512gb ram M3 Ultra mac studios
A user shares their $25k hardware setup of two 512GB RAM M3 Ultra Mac Studios for running large language models locally, having tested DeepSeek V3 Q8 and GLM 5.1 Q4 via the exo distributed inference backend, while awaiting Kimi 2.6 MLX optimization.