← Back to community benchmarks

gemma-4-31b

M4 Max (40c) · 128 GB · bf16 · 2026-04-05

Performance

1k

tokens

209.8

PP tok/s

7.7

TG tok/s

4887

TTFT (ms)

58.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.3

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	209.8	7.7	58.9 GB	current
4k	219.8	7.3	60.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	7.7	1.00×
2×	7.5	0.97×
4×	14.8	1.92×