← Back to community benchmarks

Ternary-Bonsai-27B

M1 Max (32c) · 32 GB · 2bit · 2026-07-20

Performance

64k

tokens

110.7

PP tok/s

14.0

TG tok/s

592181

TTFT (ms)

15.7

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.5.2.dev1

macOS macOS 27.0

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	151.9	26.4	10.2 GB	view
16k	140.7	24.3	11.5 GB	view
64k	110.7	14.0	15.7 GB	current