← Back to community benchmarks

Nemotron-Cascade-2-30B-A3B-oQ3.5

M5 (10c) · 32 GB · 3bit · 2026-04-28
Performance
8k
tokens
960.3
PP tok/s
51.2
TG tok/s
8532
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 768.0 55.5 15.4 GB view
4k 962.6 51.5 16.4 GB view
8k 960.3 51.2 16.5 GB current
16k 953.1 44.6 16.5 GB view
32k 900.3 32.4 16.6 GB view
Batching Results
Batch Size TG tok/s Speedup
55.5 1.00×
77.6 1.40×
80.9 1.46×