← Back to community benchmarks

Qwen3.5-9B

M5 Pro (16c) · 48 GB · 4bit · 2026-05-19

Performance

1k

tokens

1,094

PP tok/s

56.6

TG tok/s

936

TTFT (ms)

5.8

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,094	56.6	5.8 GB	current
4k	1,305	54.8	6.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	56.6	1.00×
2×	94.2	1.66×
4×	115.5	2.04×