← Back to community benchmarks

Laguna-S-2.1-oQ6e

M5 Max (40c) · 128 GB · 6bit · 2026-07-24
Performance
32k
tokens
779.2
PP tok/s
43.6
TG tok/s
42055
TTFT (ms)
88.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,012 53.9 87.0 GB view
4k 986.0 51.3 87.2 GB view
8k 923.6 53.3 87.3 GB view
16k 843.0 49.4 87.7 GB view
32k 779.2 43.6 88.5 GB current
64k 659.8 37.0 90.1 GB view
Batching Results
Batch Size TG tok/s Speedup
53.9 1.00×
69.9 1.30×
83.1 1.54×