← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 6bit · 2026-04-18
Performance
16k
tokens
3,286
PP tok/s
116.3
TG tok/s
4986
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,478 131.6 26.2 GB view
4k 2,840 123.1 27.2 GB view
8k 3,128 121.1 27.2 GB view
16k 3,286 116.3 27.3 GB current
32k 3,413 98.9 27.4 GB view
Batching Results
Batch Size TG tok/s Speedup
131.6 1.00×
183.5 1.39×
253.2 1.92×
245.7 1.87×