← Back to community benchmarks

Laguna-S-2.1

M5 Max (40c) · 128 GB · 4bit · 2026-07-21
Performance
1k
tokens
784.3
PP tok/s
72.0
TG tok/s
1307
TTFT (ms)
67.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 27.0
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 784.3 72.0 67.8 GB current
4k 967.3 69.4 68.2 GB view
Batching Results
Batch Size TG tok/s Speedup
72.0 1.00×
90.6 1.26×