← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-04-16

Performance

4k

tokens

139.9

PP tok/s

20.8

TG tok/s

29286

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	139.0	22.4	3.3 GB	view
4k	139.9	20.8	3.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	22.4	1.00×
2×	32.4	1.45×
4×	33.1	1.48×