← Back to community benchmarks

Laguna-S-2.1-oQ5e

M5 Max (40c) · 128 GB · 5bit · 2026-07-23
Performance
16k
tokens
1,024
PP tok/s
54.6
TG tok/s
15995
TTFT (ms)
74.8
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 827.1 61.2 73.6 GB view
4k 1,147 59.6 73.9 GB view
8k 1,063 56.6 74.2 GB view
16k 1,024 54.6 74.8 GB current
32k 939.4 50.1 75.9 GB view
64k 847.2 42.1 78.3 GB view
Batching Results
Batch Size TG tok/s Speedup
61.2 1.00×
81.7 1.33×
115.1 1.88×
142.5 2.33×