← Back to community benchmarks

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

M3 Max (40c) · 48 GB · 6bit · 2026-05-05

Performance

8k

tokens

1,234

PP tok/s

88.4

TG tok/s

6637

TTFT (ms)

27.2

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	1,234	88.4	27.2 GB	current
16k	1,193	75.4	27.3 GB	view