← Back to community benchmarks

gemma-4-31b-it

M2 Ultra (76c) · 192 GB · 4bit · 2026-04-24

Performance

1k

tokens

184.7

PP tok/s

26.1

TG tok/s

5544

TTFT (ms)

17.6

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 192 GB

GPU Cores 76

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	184.7	26.1	17.6 GB	current
4k	187.2	24.2	19.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	26.1	1.00×
2×	32.3	1.24×
4×	36.9	1.41×