Can the Apple M2 Ultra run Qwen3 235B-A22B?
Yes, with 192 GB or more. Qwen3 235B-A22B needs about 144 GB and the Apple M2 Ultra with 192 GB of unified memory leaves about 144 GB for models. Expect about 21 tok/s, about reading speed. The 64 and 128 GB versions don't have room.
ollama run qwen3:235bFirst time? Install Ollama, then paste that into a terminal.
Each Apple M2 Ultra version
- 64 GB (about 48 GB usable)Too big
- 128 GB (about 96 GB usable)Too big
- 192 GB (about 144 GB usable)Usable ~21 tok/s
Speed comes from memory bandwidth: the card reads all 13.3 GB of active weights for every token. On the Apple M2 Ultra, gpt-oss 120B runs at about 97 tok/s if you can trade some quality for speed. Cards that run Qwen3 235B-A22B faster:
No single card or Mac we track does. It needs a multi-GPU rig; see the builds.
Speed is roughly memory bandwidth divided by the weights read per token, calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured it yourself? Send us the number.