Datagram

Run Gemma 4 E4B on a Dedicated Mac

Gemma 4 E4B needs about 6.9 GB of memory at 4-bit. It runs on our Mac Mini M6 32GB at about 26–36 tokens per second, from $169/mo.

Macs that run Gemma 4 E4B

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

  • Mac Mini M6 32GB Best value
    26–36 tokens/sec
    from $169/mo
    Order
  • Mac Mini M5 Pro 64GB
    44–60 tokens/sec
    from $299/mo
    Order
  • Mac Studio M4 Max 128GB
    70–93 tokens/sec
    from $499/mo
    Order
  • Mac Studio M5 Max 128GB
    77–101 tokens/sec
    from $569/mo Available Nov 10, 2026
    Order
  • Mac Studio M5 Ultra 256GB
    125–155 tokens/sec
    from $1,199/mo Available Nov 16, 2026
    Order
  • 2× Mac Studio M5 Ultra 256GB Cluster Cluster
    100–118 tokens/sec
    from $2,399/mo Available Nov 16, 2026
    Order
  • Mac Studio M5 Ultra 512GB
    125–155 tokens/sec
    from $2,499/mo Available Dec 30, 2026
    Order
  • 2× Mac Studio M5 Ultra 512GB Cluster Cluster
    100–118 tokens/sec
    from $4,999/mo Available Dec 30, 2026
    Order
  • 4× Mac Studio M5 Ultra 512GB Cluster Cluster
    72–80 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.

Gemma 4 E4B is a mixture-of-experts model: of its 8 billion parameters, only about 4.5 billion are used for each word. It needs memory for all of them but runs at the speed of a much smaller model.

Similar models