Datagram

Run IBM Granite Switch 4.1 8B on a Dedicated Mac

IBM Granite Switch 4.1 8B needs about 11.8 GB of memory at 4-bit. It runs on our Mac Mini M6 32GB at about 12–16 tokens per second, from $169/mo.

Macs that run IBM Granite Switch 4.1 8B

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

  • Mac Mini M6 32GB Best value
    12–16 tokens/sec
    from $169/mo
    Order
  • Mac Mini M5 Pro 64GB
    20–29 tokens/sec
    from $299/mo
    Order
  • Mac Studio M4 Max 128GB
    35–48 tokens/sec
    from $499/mo
    Order
  • Mac Studio M5 Max 128GB
    38–53 tokens/sec
    from $569/mo Available Nov 10, 2026
    Order
  • Mac Studio M5 Ultra 256GB
    69–91 tokens/sec
    from $1,199/mo Available Nov 16, 2026
    Order
  • 2× Mac Studio M5 Ultra 256GB Cluster Cluster
    61–77 tokens/sec
    from $2,399/mo Available Nov 16, 2026
    Order
  • Mac Studio M5 Ultra 512GB
    69–91 tokens/sec
    from $2,499/mo Available Dec 30, 2026
    Order
  • 2× Mac Studio M5 Ultra 512GB Cluster Cluster
    61–77 tokens/sec
    from $4,999/mo Available Dec 30, 2026
    Order
  • 4× Mac Studio M5 Ultra 512GB Cluster Cluster
    49–59 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.

IBM Granite Switch 4.1 8B is a dense model: all 9 billion parameters are used for every word, so memory bandwidth decides its speed. The M5 Ultra's 1,229 GB/s makes the biggest difference here.

Similar models