← Back to community benchmarks

Ternary-Bonsai-27B

M3 Max (40c) · 128 GB · 2bit · 2026-07-16

Performance

128k

tokens

94.7

PP tok/s

9.2

TG tok/s

1384602

TTFT (ms)

25.4

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	120.2	12.3	13.9 GB	view
128k	94.7	9.2	25.4 GB	current