← Back to community benchmarks

Laguna-S-2.1-NVFP4

M5 Max (40c) · 128 GB · 4bit · 2026-07-24
Performance
16k
tokens
1,030
PP tok/s
39.4
TG tok/s
15904
TTFT (ms)
68.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 593.0 43.1 67.7 GB view
4k 1,143 42.4 67.9 GB view
8k 1,076 41.1 68.3 GB view
16k 1,030 39.4 68.8 GB current
32k 943.9 36.4 70.0 GB view
64k 842.4 32.1 72.3 GB view
128k 611.6 24.1 77.0 GB view
195k 472.8 18.6 83.5 GB view
Batching Results
Batch Size TG tok/s Speedup
43.1 1.00×
35.3 0.82×
61.6 1.43×