← Back to community benchmarks

gemma-3-4b-it-qat

M1 Pro (16c) · 16 GB · 4bit · 2026-03-12

Performance

1k

tokens

314.5

PP tok/s

55.5

TG tok/s

3259

TTFT (ms)

3.6

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 16 GB

GPU Cores 16

Software

oMLX v0.2.8

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	314.5	55.5	3.6 GB	current
4k	325.5	53.0	3.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	55.5	1.00×
2×	55.2	0.99×
4×	65.8	1.19×