← Back to community benchmarks

NVIDIA-Nemotron-3-Nano-30B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-04-29
Performance
64k
tokens
1,412
PP tok/s
38.2
TG tok/s
46422
TTFT (ms)
34.9
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8.dev3
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,319 65.4 33.5 GB view
4k 1,793 62.3 34.6 GB view
8k 1,855 61.7 34.6 GB view
16k 1,845 58.4 34.6 GB view
32k 1,711 49.9 34.7 GB view
64k 1,412 38.2 34.9 GB current
Batching Results
Batch Size TG tok/s Speedup
65.4 1.00×
81.2 1.24×
98.5 1.51×
110.6 1.69×