← Back to community benchmarks

Laguna-XS-2.1

M5 Pro (20c) · 48 GB · 4bit · 2026-07-23
Performance
195k
tokens
482.3
PP tok/s
23.1
TG tok/s
414664
TTFT (ms)
26.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,660 95.9 18.1 GB view
4k 1,487 90.4 18.2 GB view
8k 1,391 84.9 18.4 GB view
16k 1,303 76.1 18.7 GB view
32k 1,159 62.0 19.4 GB view
64k 936.6 45.7 20.8 GB view
128k 684.8 32.2 23.5 GB view
195k 482.3 23.1 26.2 GB current
Batching Results
Batch Size TG tok/s Speedup
95.9 1.00×
137.5 1.43×
185.6 1.94×
231.5 2.41×