Run Qwen3.8 Flash-Next 180B on a Dedicated Mac

Macs that run Qwen3.8 Flash-Next 180B

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

• Mac Studio M4 Max 128GB
  57–77 tokens/sec · tight fit
  from $499/mo
  Order
• Mac Studio M5 Max 128GB
  63–84 tokens/sec · tight fit
  from $569/mo Available Nov 10, 2026
  Order
• Mac Studio M5 Ultra 256GB Best value
  106–134 tokens/sec
  from $1,199/mo Available Nov 16, 2026
  Order
• 2× Mac Studio M5 Ultra 256GB Cluster Cluster
  87–106 tokens/sec
  from $2,399/mo Available Nov 16, 2026
  Order
• Mac Studio M5 Ultra 512GB
  106–134 tokens/sec
  from $2,499/mo Available Dec 30, 2026
  Order
• 2× Mac Studio M5 Ultra 512GB Cluster Cluster
  87–106 tokens/sec
  from $4,999/mo Available Dec 30, 2026
  Order
• 4× Mac Studio M5 Ultra 512GB Cluster Cluster
  65–74 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.

Qwen3.8 Flash-Next 180B is a mixture-of-experts model: of its 180 billion parameters, only about 6 billion are used for each word. It needs memory for all of them but runs at the speed of a much smaller model.