← Back to community benchmarks

Qwen3.5-4B

M4 (10c) · 32 GB · 4bit · 2026-03-09

Performance

1k

tokens

351.7

PP tok/s

36.2

TG tok/s

2912

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 15.7.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	351.7	36.2	3.9 GB	current
4k	343.2	34.5	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	36.2	1.00×
2×	69.4	1.92×
4×	76.7	2.12×