alt Hacker News> M6 supports up to 32GB of unified memory to multitask across demanding apps and run LLMs on device for secure and private agentic tasks. It also provides up to 170GB/s of unified memory bandwidth — a 10 percent increase over M5 and a 2.5x increase over M1.
Isn't 170GB/s slow for bandwidth?
Replies
It's higher bandwidth than any dual-channel DDR5 desktop machine, but Apple never quote the memory latency, so hard to compare otherwise.
For max memory bandwidth you need to buy the Ultra versions (M5 Ultra: 1,2TB/s, this gets comparable to real GPUs regarding the memory bandwidth).
M6 and M5 Ultra both have comparable memory bandwidth per GPU core. I think they will perform well.
It's fast by computer standards and excellent for entry level chip. The Pro/Max/Ultra chips are always faster.
Compared to something like VRAM it's slow.
You would want to get the M5 pro version with 307gb/s if you were interested in running local LLMs.
Kinda. Strix Halo does 256GB/s of memory bandwidth, and is significantly slower than an M5 Max (614GB/s). Feels like intentional market segmentation?
It is. That's the mac mini. For local LLMs you would want the Mac Studio, which tops out at 1.2TB/s.