← Back to community benchmarks

Qwen3-4B-Instruct-2507

M4 (8c) · 16 GB · 4bit · 2026-03-12

Performance

1k

tokens

296.7

PP tok/s

37.7

TG tok/s

3451

TTFT (ms)

2.8

Peak mem (GB)

Hardware

Chip M4 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.8

macOS macOS 26.3.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	37.7	1.00×
2×	65.8	1.75×