← Back to community benchmarks

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

M5 Pro (20c) · 64 GB · 8bit · 2026-04-27
Performance
16k
tokens
1,539
PP tok/s
64.5
TG tok/s
10646
TTFT (ms)
50.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,325 66.4 49.1 GB view
4k 1,747 64.9 50.1 GB view
8k 1,832 63.1 50.1 GB view
16k 1,539 64.5 50.2 GB current
32k 1,466 64.6 50.3 GB view
Batching Results
Batch Size TG tok/s Speedup
66.4 1.00×
90.0 1.36×
110.3 1.66×
124.8 1.88×