← Back to community benchmarks

gemma-4-31b-it-5bit

M2 Max (30c) · 64 GB · 5bit · 2026-04-28

Performance

4k

tokens

72.6

PP tok/s

6.0

TG tok/s

56441

TTFT (ms)

22.9

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.5.dev1

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	72.7	11.2	21.1 GB	view
4k	72.6	6.0	22.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	11.2	1.00×
2×	8.4	0.75×
4×	12.7	1.13×