Run Qwen3 235B-A22B on a Dedicated Mac

Macs that run Qwen3 235B-A22B

At 4-bit with a 32K-token context. Speeds are estimates; see real measurements on the calculator page.

• Mac Studio M5 Ultra 256GB Best value
  36–49 tokens/sec
  from $1,199/mo Available Nov 16, 2026
  Order
• 2× Mac Studio M5 Ultra 256GB Cluster Cluster
  33–45 tokens/sec
  from $2,399/mo Available Nov 16, 2026
  Order
• Mac Studio M5 Ultra 512GB
  36–49 tokens/sec
  from $2,499/mo Available Dec 30, 2026
  Order
• 2× Mac Studio M5 Ultra 512GB Cluster Cluster
  33–45 tokens/sec
  from $4,999/mo Available Dec 30, 2026
  Order
• 4× Mac Studio M5 Ultra 512GB Cluster Cluster
  29–38 tokens/sec
  from $9,999/mo Available Dec 30, 2026
  Order

Why it runs well on a Mac

Language models have to sit entirely in memory, and generating each word means reading through them again. Apple Silicon puts up to 512 GB of fast unified memory on one chip that the GPU can use directly, so a model like this fits on one quiet machine instead of a stack of graphics cards.

Qwen3 235B-A22B is a mixture-of-experts model: of its 235 billion parameters, only about 22 billion are used for each word. It needs memory for all of them but runs at the speed of a much smaller model.