← Back to community benchmarks

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

M3 Max (40c) · 64 GB · 4bit · 2026-03-17
Performance
4k
tokens
1,284
PP tok/s
118.9
TG tok/s
3191
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.18
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,094 124.3 18.8 GB view
4k 1,284 118.9 19.9 GB current
64k 978.4 71.5 20.2 GB view
Batching Results
Batch Size TG tok/s Speedup
124.3 1.00×
178.5 1.44×
217.1 1.75×