← Back to community benchmarks

Nemotron-Cascade-2-30B-A3B

M5 Pro (20c) · 64 GB · 6bit · 2026-03-26
Performance
32k
tokens
1,621
PP tok/s
63.4
TG tok/s
20221
TTFT (ms)
27.4
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.21
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,426 80.6 26.1 GB view
4k 1,788 78.6 27.2 GB view
8k 1,832 75.6 27.2 GB view
16k 1,772 70.5 27.3 GB view
32k 1,621 63.4 27.4 GB current
Batching Results
Batch Size TG tok/s Speedup
80.6 1.00×
115.1 1.43×
139.6 1.73×