← Back to community benchmarks

Qwen3.5-9B

M3 Max · 16 GB · 4bit · 2026-03-23

Performance

4k

tokens

538.9

PP tok/s

49.9

TG tok/s

7601

TTFT (ms)

7.3

Peak mem (GB)

Hardware

Chip M3 Max

Memory 16 GB

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	505.4	53.6	6.5 GB	view
4k	538.9	49.9	7.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	53.6	1.00×
2×	92.9	1.73×
4×	113.2	2.11×