← Back to community benchmarks

Qwen3.5-4B

M4 (10c) · 16 GB · 4bit · 2026-03-09

Performance

8k

tokens

390.9

PP tok/s

33.4

TG tok/s

20958

TTFT (ms)

4.6

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 15.7.3

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	406.1	37.5	3.9 GB	view
4k	403.9	34.7	4.2 GB	view
8k	390.9	33.4	4.6 GB	current
16k	351.7	27.9	4.8 GB	view