← Back to community benchmarks

Qwen3.5-9B

M4 Max (40c) · 64 GB · 4bit · 2026-03-09

Performance

1k

tokens

877.9

PP tok/s

87.1

TG tok/s

1166

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.2.6

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	877.9	87.1	6.7 GB	current
4k	883.5	84.5	7.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	87.1	1.00×
2×	163.2	1.87×
4×	192.3	2.21×