← Back to community benchmarks

Qwen3-1.7B

M4 Pro (16c) · 48 GB · 8bit · 2026-03-12

Performance

1k

tokens

1,384

PP tok/s

104.7

TG tok/s

740

TTFT (ms)

2.4

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.8

macOS macOS 15.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,384	104.7	2.4 GB	current
4k	1,419	82.9	2.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	104.7	1.00×
2×	179.6	1.72×
4×	220.8	2.11×