← Back to community benchmarks

Laguna-S-2.1-NVFP4

M3 Ultra (60c) · 256 GB · 4bit · 2026-07-23
Performance
8k
tokens
651.6
PP tok/s
43.2
TG tok/s
12575
TTFT (ms)
68.0
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 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 651.6 43.2 68.0 GB current
16k 611.0 41.6 68.8 GB view
32k 557.3 38.8 69.9 GB view
64k 471.9 34.4 72.3 GB view