M5 ultra Ram setup : pooling vote

<!-- SC_OFF --><div class="md"><p>I could fit the Q3 model not sure if it's worth over 27B ? </p> </div><!-- SC_ON --> &#32; submitted by &#32; <a

<!-- SC_OFF --><div class="md"><p>Currently using glm 4.7 flash, it’s very meh </p> <p>Heard omnicoder or Crow 9b are good, are they any better?</p> <p>Or Qwen3.5 27b?</p>

<!-- SC_OFF --><div class="md"><p>I am currently on an m3 mbp with 24gb ram. For regular python and django work the machine is perfect and i have no need to upgrade for speed. but

<!-- SC_OFF --><div class="md"><p>Hey, </p> <p>Tldr: use local models like qwen 3.5 quantized with proprietary models for fire and forget work. Local model doing the grunt work.

<!-- SC_OFF --><div class="md"><p>Any thoughts on how much UM there will be in the new Mac Studio? Also, do you think Apple will release it a their event in June this summer?</p>

<!-- SC_OFF --><div class="md"><p>I've been circling this decision for weeks and could use some outside perspective.</p> <p>What I'm looking at: Mac Studio, M5 Max, 128GB unified

<!-- SC_OFF --><div class="md"><p>Just had a look at un-binned 256gb M5 Ultras and the wait is now ~18 weeks. Since you don't pay until it ships, surely there decent chance prices