← Back to community benchmarks

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

M4 Max (40c) · 64 GB · 4bit · 2026-03-13
Performance
1k
tokens
1,136
PP tok/s
152.2
TG tok/s
901
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,136 152.2 18.2 GB current
4k 1,523 145.1 18.3 GB view
Batching Results
Batch Size TG tok/s Speedup
152.2 1.00×
214.1 1.41×
270.8 1.78×