← Back to community benchmarks

Laguna-S-2.1-oQ4e

M5 Max (40c) · 128 GB · 4bit · 2026-07-22
Performance
4k
tokens
1,034
PP tok/s
60.0
TG tok/s
3962
TTFT (ms)
60.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 27.0
Context 4,096
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 current
16k 893.7 54.6 61.3 GB view
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×