← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-12

Performance

1k

tokens

66.0

PP tok/s

12.8

TG tok/s

15506

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.9

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	66.0	12.8	3.9 GB	current
4k	63.1	8.7	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.8	1.00×
2×	15.4	1.20×
4×	14.4	1.12×