Run DeepSeek V4.1 Flash 763B on a Dedicated Mac

Macs that run DeepSeek V4.1 Flash 763B

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

• 2× Mac Studio M5 Ultra 256GB Cluster Cluster
  45–59 tokens/sec · tight fit
  from $2,399/mo Available Nov 16, 2026
  Order
• Mac Studio M5 Ultra 512GB
  49–66 tokens/sec · tight fit
  from $2,499/mo Available Dec 30, 2026
  Order
• 2× Mac Studio M5 Ultra 512GB Cluster Best value Cluster
  45–59 tokens/sec
  from $4,999/mo Available Dec 30, 2026
  Order
• 4× Mac Studio M5 Ultra 512GB Cluster Cluster
  38–48 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.

DeepSeek V4.1 Flash 763B is a mixture-of-experts model: of its 763 billion parameters, only about 16 billion are used for each word. It needs memory for all of them but runs at the speed of a much smaller model.