← Back to community benchmarks

Nemotron-Cascade-2-30B-A3B

M1 Max (32c) · 64 GB · 4bit · 2026-03-22

Performance

1k

tokens

470.1

PP tok/s

77.4

TG tok/s

2181

TTFT (ms)

18.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	470.1	77.4	18.8 GB	current
4k	515.3	73.0	19.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	77.4	1.00×
2×	98.6	1.27×
4×	114.3	1.48×