← Back to community benchmarks

Laguna-S-2.1-oQ4e-fast

M5 Max (40c) · 128 GB · 4bit · 2026-07-24
Performance
128k
tokens
560.9
PP tok/s
26.9
TG tok/s
233668
TTFT (ms)
69.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 906.2 67.5 59.8 GB view
4k 1,165 65.3 60.1 GB view
8k 987.6 62.7 60.4 GB view
16k 927.4 57.7 61.0 GB view
32k 852.2 49.1 62.1 GB view
64k 763.4 42.2 64.5 GB view
128k 560.9 26.9 69.2 GB current