← Back to community benchmarks

Qwen3.5-4B

M5 Max (40c) · 128 GB · 8bit · 2026-05-15

Performance

1k

tokens

2,247

PP tok/s

94.1

TG tok/s

456

TTFT (ms)

5.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,247	94.1	5.3 GB	current
4k	3,900	86.9	6.0 GB	view
8k	3,763	88.4	6.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	94.1	1.00×
2×	184.1	1.96×
4×	235.8	2.51×