← Back to community benchmarks

Qwen3.5-9B

M5 Pro (20c) · 64 GB · 4bit · 2026-07-05

Performance

1k

tokens

1,162

PP tok/s

56.0

TG tok/s

882

TTFT (ms)

5.8

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9.dev1

macOS macOS 27.0

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,162	56.0	5.8 GB	current
4k	1,557	54.8	6.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	56.0	1.00×
2×	102.7	1.83×
4×	112.4	2.01×