Can I run Qwen3 235B A22B Thinking 2507 on Apple M2 Ultra (76-core GPU)?

This one is close. The answer rests on a file size we calculated from the parameter count rather than measured. A 10% error in that size changes the verdict, so treat it as a maybe and test before you buy.

148.2 GB of weights, plus 6 GB for the software that runs it and the smallest conversation it can hold, comes to 154.2 GB against the 144 GB this 192 GB device leaves free.

Qwen3 235B A22B Thinking 2507 is hosted by 5 providers from $2.30 per 1M output tokens (DeepInfra).Compare providers →