← Back to community benchmarks

Laguna-S-2.1-oQ5e

M5 Max (40c) · 128 GB · 5bit · 2026-07-22
Performance
16k
tokens
792.0
PP tok/s
45.5
TG tok/s
20687
TTFT (ms)
74.3
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 1,043 32.5 73.6 GB view
4k 846.6 54.8 73.8 GB view
16k 792.0 45.5 74.3 GB current
32k 727.6 46.9 75.1 GB view
64k 658.8 40.2 76.7 GB view
128k 443.5 20.5 80.0 GB view
Batching Results
Batch Size TG tok/s Speedup
32.5 1.00×
65.4 2.01×
105.0 3.23×