← Back to community benchmarks

Nemotron-Cascade-2-30B-A3B

M1 Max (24c) · 32 GB · 4bit · 2026-04-29
Performance
16k
tokens
401.8
PP tok/s
51.2
TG tok/s
40775
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 369.1 65.3 18.9 GB view
4k 413.7 62.2 19.8 GB view
8k 411.8 58.8 19.9 GB view
16k 401.8 51.2 19.9 GB current
32k 374.7 42.4 20.0 GB view
64k 328.0 28.5 20.2 GB view
Batching Results
Batch Size TG tok/s Speedup
65.3 1.00×
80.3 1.23×