← Back to community benchmarks

gemma-4-31B-it

M1 Ultra (48c) · 128 GB · 4bit · 2026-04-23

Performance

4k

tokens

108.3

PP tok/s

13.6

TG tok/s

37825

TTFT (ms)

29.0

Peak mem (GB)

Hardware

Chip M1 Ultra (48c)

Memory 128 GB

GPU Cores 48

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	107.8	15.3	27.3 GB	view
4k	108.3	13.6	29.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.3	1.00×
2×	20.5	1.34×
4×	23.4	1.53×