← Back to community benchmarks

Qwen3.5-4B

M2 (10c) · 8 GB · 4bit · 2026-03-12

Performance

4k

tokens

199.8

PP tok/s

30.5

TG tok/s

20498

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 8 GB

GPU Cores 10

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	201.9	32.3	3.9 GB	view
4k	199.8	30.5	4.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.3	1.00×
2×	45.2	1.40×
4×	46.9	1.45×