Bro borrowed his mom’s iPhone and turned it into a second GPU for his MacBook.
Backburner runs Qwen 3.8 27B across a 24GB M4 Pro MacBook and an iPhone 17 Pro Max, connected by a 10Gb/s USB-C cable. How does a 27B model fit? It uses IQ4_XS quantization, roughly 4 bits per
Qwen 3.8 Max with the same prompt as Fable 5.5 earlier on my timeline.
This is the second best one in my opinion. GLM-5.3 is the last one and should be ready soon.
I asked Qwen 3.8 to create an ASCII butterfly so it wrote this whole thing completely in code.
I was at the DevFest Bay Area meetup at the circuitlaunch coworking space in Mountain View held yesterday and it was a great experience.
As a bonus we got 2nd place in a hackathon! What we built: a local AI control plane that intelligently routes requests between local models
You have reached the end of the archive
All of qwen38