← Back to community benchmarks

Qwen3.5-4B

M2 (10c) · 16 GB · 4bit · 2026-03-09

Performance

4k

tokens

186.2

PP tok/s

24.3

TG tok/s

21995

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	193.0	25.1	3.9 GB	view
4k	186.2	24.3	4.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	25.1	1.00×
2×	22.8	0.91×
4×	23.8	0.95×