← Back to community benchmarks

Qwen3.5-9B

M1 Max (24c) · 32 GB · 4bit · 2026-03-12

Performance

4k

tokens

159.9

PP tok/s

23.6

TG tok/s

25622

TTFT (ms)

7.0

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.2.9

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	166.9	24.5	6.7 GB	view
4k	159.9	23.6	7.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	24.5	1.00×
2×	29.0	1.18×
4×	33.9	1.38×