← Back to community benchmarks

Laguna-S-2.1-oQ6e

M5 Max (40c) · 128 GB · 6bit · 2026-07-23
Performance
64k
tokens
522.6
PP tok/s
27.6
TG tok/s
125395
TTFT (ms)
98.2
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 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 677.6 51.3 87.0 GB view
4k 712.3 51.4 87.3 GB view
8k 733.0 47.6 87.7 GB view
16k 695.0 46.3 89.2 GB view
32k 658.7 38.4 92.2 GB view
64k 522.6 27.6 98.2 GB current
128k 314.9 16.7 110.2 GB view
Batching Results
Batch Size TG tok/s Speedup
51.3 1.00×
31.8 0.62×
41.1 0.80×