← Back to community benchmarks

gemma-4-E4B-it-oQ4

M4 Max (40c) · 64 GB · 4bit · 2026-04-25

Performance

1k

tokens

1,622

PP tok/s

101.1

TG tok/s

632

TTFT (ms)

4.8

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,622	101.1	4.8 GB	current
4k	2,115	90.5	4.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	101.1	1.00×
2×	176.8	1.75×
4×	224.3	2.22×