← Back to community benchmarks

Laguna-S-2.1-NVFP4

M5 Max (40c) · 128 GB · 4bit · 2026-07-22
Performance
64k
tokens
894.9
PP tok/s
32.3
TG tok/s
73235
TTFT (ms)
71.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 605.4 44.6 67.7 GB view
4k 1,183 43.7 67.9 GB view
64k 894.9 32.3 71.0 GB current
Batching Results
Batch Size TG tok/s Speedup
44.6 1.00×
36.6 0.82×
65.7 1.47×