← Back to community benchmarks

Laguna-XS-2.1

M3 Ultra (60c) · 256 GB · 8bit · 2026-07-22
Performance
32k
tokens
1,012
PP tok/s
70.5
TG tok/s
32380
TTFT (ms)
35.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
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 1,740 87.6 33.7 GB view
4k 1,422 84.0 33.8 GB view
8k 1,306 81.2 34.0 GB view
16k 1,179 76.9 34.3 GB view
32k 1,012 70.5 35.0 GB current
64k 790.3 59.7 36.3 GB view
Batching Results
Batch Size TG tok/s Speedup
87.6 1.00×
140.7 1.61×
223.9 2.56×
314.3 3.59×