← Back to community benchmarks

Qwen3.5-9B

M5 (8c) · 16 GB · 4bit · 2026-03-17

Performance

4k

tokens

608.6

PP tok/s

26.6

TG tok/s

6730

TTFT (ms)

7.3

Peak mem (GB)

Hardware

Chip M5 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.17

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	617.3	27.4	6.5 GB	view
4k	608.6	26.6	7.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.4	1.00×
2×	51.7	1.89×
4×	54.0	1.97×