← Back to community benchmarks

Laguna-S-2.1-oQ4e

M5 Max (40c) · 128 GB · 4bit · 2026-07-24
Performance
32k
tokens
788.5
PP tok/s
44.3
TG tok/s
41561
TTFT (ms)
62.0
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 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 786.3 62.9 60.6 GB view
4k 1,093 61.6 60.7 GB view
8k 1,030 60.4 60.9 GB view
16k 963.1 52.8 61.3 GB view
32k 788.5 44.3 62.0 GB current
64k 723.4 40.0 63.6 GB view
Batching Results
Batch Size TG tok/s Speedup
62.9 1.00×
88.3 1.40×
104.2 1.66×
237.4 3.77×