← Back to community benchmarks

Nemotron-3-Nano-30B-A3B-TurboQuant

M5 Pro (20c) · 64 GB · 8bit · 2026-05-04
Performance
8k
tokens
1,897
PP tok/s
64.8
TG tok/s
4318
TTFT (ms)
35.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,411 67.5 34.1 GB view
4k 1,871 65.7 35.3 GB view
8k 1,897 64.8 35.3 GB current
16k 4,760 66.7 35.1 GB view
32k 4,666 65.9 35.2 GB view
64k 4,323 63.8 35.3 GB view
Batching Results
Batch Size TG tok/s Speedup
67.5 1.00×
89.5 1.33×
111.2 1.65×
125.7 1.86×