← Back to community benchmarks

Qwen3.5-9B

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

Performance

1k

tokens

1,250

PP tok/s

57.6

TG tok/s

819

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.12

macOS macOS 26.3

Context 1,024

Performance by Context Length

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

Batching Results

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