← Back to community benchmarks

Qwen3.5-2B

M4 (10c) · 32 GB · 8bit · 2026-03-09

Performance

4k

tokens

1,043

PP tok/s

45.4

TG tok/s

3927

TTFT (ms)

3.4

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 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	1,014	46.9	3.2 GB	view
4k	1,043	45.4	3.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	46.9	1.00×
2×	92.4	1.97×
4×	152.2	3.25×