← Back to community benchmarks

Laguna-S-2.1-oQ4e

M5 Max (40c) · 128 GB · 4bit · 2026-07-22
Performance
16k
tokens
893.7
PP tok/s
54.6
TG tok/s
18334
TTFT (ms)
61.3
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 1,029 61.3 60.6 GB view
4k 1,034 60.0 60.7 GB view
16k 893.7 54.6 61.3 GB current
32k 761.9 48.8 62.0 GB view
64k 659.0 32.5 63.6 GB view
128k 393.2 18.8 66.9 GB view
Batching Results
Batch Size TG tok/s Speedup
61.3 1.00×
59.6 0.97×
122.6 2.00×