← Back to community benchmarks

gemma-3-4b-it-qat

M1 (8c) · 16 GB · 4bit · 2026-03-11

Performance

1k

tokens

161.2

PP tok/s

23.2

TG tok/s

6358

TTFT (ms)

3.5

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	161.2	23.2	3.5 GB	current
4k	160.5	22.8	3.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.2	1.00×
2×	16.9	0.73×
4×	23.1	1.00×