← Back to community benchmarks

gemma-4-e4b-it

M1 Max (24c) · 64 GB · 4bit · 2026-05-23

Performance

64k

tokens

449.0

PP tok/s

17.8

TG tok/s

145949

TTFT (ms)

7.2

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	687.2	66.6	5.8 GB	view
4k	690.3	61.1	5.8 GB	view
64k	449.0	17.8	7.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	66.6	1.00×
2×	45.3	0.68×
4×	53.6	0.80×