← Back to community benchmarks

Qwen3.5-9B

M5 Pro (16c) · 48 GB · 4bit · 2026-03-14

Performance

4k

tokens

1,269

PP tok/s

54.1

TG tok/s

3227

TTFT (ms)

7.0

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.12

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,250	57.6	6.7 GB	view
4k	1,269	54.1	7.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	57.6	1.00×
2×	95.5	1.66×
4×	115.0	2.00×