← Back to community benchmarks

Qwen3.5-9B

M2 Pro (19c) · 16 GB · 4bit · 2026-03-12

Performance

4k

tokens

207.1

PP tok/s

33.9

TG tok/s

19783

TTFT (ms)

7.0

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 16 GB

GPU Cores 19

Software

oMLX v0.2.9

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	206.0	36.3	6.7 GB	view
4k	207.1	33.9	7.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	36.3	1.00×
2×	47.0	1.29×
4×	49.0	1.35×