← Back to community benchmarks

gemma-4-31b

M1 Ultra (64c) · 128 GB · bf16 · 2026-04-26

Performance

1k

tokens

168.4

PP tok/s

9.0

TG tok/s

6087

TTFT (ms)

58.9

Peak mem (GB)

Hardware

Chip M1 Ultra (64c)

Memory 128 GB

GPU Cores 64

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	168.4	9.0	58.9 GB	current
4k	177.1	8.3	60.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	9.0	1.00×
2×	5.4	0.60×
4×	10.3	1.14×