← Back to community benchmarks

Qwen3.5-4B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-03-16

Performance

8k

tokens

385.7

PP tok/s

29.6

TG tok/s

21237

TTFT (ms)

4.3

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.13

macOS macOS 15.7.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	375.3	32.6	3.8 GB	view
4k	394.7	31.3	4.1 GB	view
8k	385.7	29.6	4.3 GB	current
16k	353.5	26.4	4.8 GB	view
32k	310.2	20.6	5.8 GB	view