← Back to community benchmarks

Laguna-S-2.1-oQ4e

M3 Max (40c) · 128 GB · 4bit · 2026-07-22

Performance

195k

tokens

147.9

PP tok/s

13.9

TG tok/s

1351825

TTFT (ms)

70.3

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 200,000

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	244.4	14.9	63.6 GB	view
195k	147.9	13.9	70.3 GB	current