← Back to community benchmarks

Laguna-XS-2.1

M5 Max (40c) · 128 GB · 8bit · 2026-07-22
Performance
16k
tokens
2,119
PP tok/s
87.7
TG tok/s
7734
TTFT (ms)
35.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 27.0
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,835 97.4 33.7 GB view
4k 2,347 92.7 33.8 GB view
16k 2,119 87.7 35.7 GB current
32k 1,843 78.0 38.2 GB view
64k 1,505 64.5 43.2 GB view
128k 1,106 48.8 53.2 GB view
Batching Results
Batch Size TG tok/s Speedup
97.4 1.00×
149.8 1.54×
234.5 2.41×
466.6 4.79×