← Back to community benchmarks

Laguna-XS-2.1

M5 Pro (20c) · 48 GB · 4bit · 2026-07-23
Performance
8k
tokens
1,332
PP tok/s
76.3
TG tok/s
6151
TTFT (ms)
18.6
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.5.2.dev1
macOS macOS 26.5.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,121 85.4 18.1 GB view
4k 1,629 82.0 18.3 GB view
8k 1,332 76.3 18.6 GB current
16k 1,465 66.2 19.0 GB view
32k 1,085 55.4 20.0 GB view
64k 841.0 42.8 22.0 GB view
Batching Results
Batch Size TG tok/s Speedup
85.4 1.00×
119.9 1.40×
176.2 2.06×