← Back to community benchmarks

gemma-4-E2B-Heretic-Uncensored

M5 Max (40c) · 128 GB · 4bit · 2026-05-18

Performance

1k

tokens

2,160

PP tok/s

192.5

TG tok/s

474

TTFT (ms)

6.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	192.5	1.00×
2×	348.2	1.81×
4×	544.1	2.83×
8×	640.2	3.33×