Run Flint 40B on a Dedicated Mac

Macs that run Flint 40B

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

• Mac Mini M6 32GB
  41–56 tokens/sec · tight fit
  from $169/mo
  Order
• Mac Mini M5 Pro 64GB Best value
  68–90 tokens/sec
  from $299/mo
  Order
• Mac Studio M4 Max 128GB
  104–132 tokens/sec
  from $499/mo
  Order
• Mac Studio M5 Max 128GB
  113–141 tokens/sec
  from $569/mo Available Nov 10, 2026
  Order
• Mac Studio M5 Ultra 256GB
  168–199 tokens/sec
  from $1,199/mo Available Nov 16, 2026
  Order
• 2× Mac Studio M5 Ultra 256GB Cluster Cluster
  126–142 tokens/sec
  from $2,399/mo Available Nov 16, 2026
  Order
• Mac Studio M5 Ultra 512GB
  168–199 tokens/sec
  from $2,499/mo Available Dec 30, 2026
  Order
• 2× Mac Studio M5 Ultra 512GB Cluster Cluster
  126–142 tokens/sec
  from $4,999/mo Available Dec 30, 2026
  Order
• 4× Mac Studio M5 Ultra 512GB Cluster Cluster
  84–91 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.

Flint 40B is a mixture-of-experts model: of its 39.8 billion parameters, only about 2.5 billion are used for each word. It needs memory for all of them but runs at the speed of a much smaller model.