← Back to community benchmarks

Qwen3.5-9B

M2 Max (38c) · 64 GB · 4bit · 2026-04-15

Performance

1k

tokens

361.1

PP tok/s

60.7

TG tok/s

2835

TTFT (ms)

5.8

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 64 GB

GPU Cores 38

Software

oMLX v0.3.5

macOS macOS 26.0

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	361.1	60.7	5.8 GB	current
4k	386.5	58.3	6.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	60.7	1.00×
2×	84.5	1.39×
4×	90.5	1.49×