← Back to community benchmarks

Laguna-S-2.1-NVFP4

M3 Ultra (60c) · 256 GB · 4bit · 2026-07-23

Performance

16k

tokens

611.0

PP tok/s

41.6

TG tok/s

26818

TTFT (ms)

68.8

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	651.6	43.2	68.0 GB	view
16k	611.0	41.6	68.8 GB	current
32k	557.3	38.8	69.9 GB	view
64k	471.9	34.4	72.3 GB	view