← Back to community benchmarks

Qwen3-0.6B

M4 (10c) · 32 GB · 4bit · 2026-03-14

Performance

4k

tokens

1,890

PP tok/s

93.7

TG tok/s

2168

TTFT (ms)

1.3

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.2.11

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,063	167.6	1.0 GB	view
4k	1,890	93.7	1.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	167.6	1.00×
2×	254.2	1.52×
4×	311.9	1.86×