← Back to community benchmarks

Qwen3.5-9B

M1 Max (24c) · 32 GB · 4bit · 2026-03-11

Performance

1k

tokens

220.6

PP tok/s

42.8

TG tok/s

4641

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.2.6

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	220.6	42.8	6.7 GB	current
4k	202.2	37.3	7.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	42.8	1.00×
2×	49.4	1.15×
4×	54.2	1.27×