← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 4bit · 2026-03-10

Performance

1k

tokens

1,096

PP tok/s

147.0

TG tok/s

935

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.6

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,096	147.0	18.2 GB	current
4k	1,480	149.7	18.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	147.0	1.00×
2×	230.1	1.57×
4×	288.1	1.96×