← Back to community benchmarks

Qwen3.5-9B

M4 Max (32c) · 36 GB · 4bit · 2026-03-15

Performance

1k

tokens

699.6

PP tok/s

69.4

TG tok/s

1464

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.2.12

macOS macOS 15.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	699.6	69.4	6.7 GB	current
4k	713.2	66.5	7.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	69.4	1.00×
2×	133.0	1.92×
4×	156.5	2.26×