← Back to community benchmarks

Qwen3.5-4B

M4 (8c) · 16 GB · 4bit · 2026-03-11

Performance

4k

tokens

294.1

PP tok/s

34.8

TG tok/s

13925

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M4 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	285.2	33.9	3.9 GB	view
4k	294.1	34.8	4.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.9	1.00×
2×	66.0	1.95×
4×	70.5	2.08×