← Back to community benchmarks

Qwen3.5-4B

M2 (10c) · 8 GB · 4bit · 2026-03-11

Performance

1k

tokens

202.0

PP tok/s

32.2

TG tok/s

5069

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 8 GB

GPU Cores 10

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	202.0	32.2	3.9 GB	current
4k	199.9	30.4	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.2	1.00×
2×	45.2	1.40×
4×	39.9	1.24×