M5 Max Mac with 128 GB

Ternary Bonsai 2 27B writes 40 tokens per second on the M5 Max Mac with 128 GB.

Ternary Bonsai 2 27B

40tokens per second

Much faster than reading

A 300-word answer in about 10 s

What 40 tokens per second looks like

Measured on 2 Macs

Ternary Bonsai 2 27B on the M5 Max Mac with 128 GB

Every model on the M5 Max Mac with 128 GB

  1. Ternary Bonsai 2 27B2 Macs40tok/s
  2. Qwen3.8 27B Max QualityFirst word 1.0 s · 2 Macs11tok/s
Questions
What's the fastest AI model on the M5 Max Mac with 128 GB?
Ternary Bonsai 2 27B, at 40 tokens per second, measured in Loci on 2 Macs.
Can the M5 Max Mac with 128 GB run Ternary Bonsai 2 27B?
Yes: Ternary Bonsai 2 27B writes 40 tokens per second on the M5 Max Mac with 128 GB, much faster than reading.
Can the M5 Max Mac with 128 GB run Qwen3.8 27B Max Quality?
Yes: Qwen3.8 27B Max Quality writes 11 tokens per second on the M5 Max Mac with 128 GB, faster than reading, with the first word in 1.0 s.
All numbers
Every model on the M5 Max Mac with 128 GB (M5 Max, 128 GB), 2026-09-22 to 2026-10-22
ModelTokens per secondTypical rangeFirst wordDevicesAnswers
Ternary Bonsai 2 27B40——2—
Qwen3.8 27B Max Quality11—1.0 s2—

Run Ternary Bonsai 2 27B on your Mac

Loci is free, needs no account, and keeps every conversation on your device.

Download for Mac

Last 30 days, through · updated daily

How these speeds are measured

  • Every number comes from real chats in Loci, timed on the device that wrote the answer, with Loci's default settings.
  • Tokens per second is how fast an answer is written once it starts. On phones, four characters of text count as one token for every model; on a Mac, Loci counts the model's own tokens. Reading pace is about 5.
  • First word is how long an answer takes to start after you send a message. Longer conversations take longer.
  • Each device counts once. The large number is the median; the typical range covers the middle half of devices.
  • Each phone speed comes from at least 10 phones. Fewer Macs run Loci, so each Mac speed says how many Macs it comes from.
  • On phones, answers written in Low Power Mode or Battery Saver, in the background, or with web search or other tools are left out.