← Back to community benchmarks

Qwen3.5-0.8B

M2 Pro (16c) · 32 GB · unknown · 2026-03-11

Performance

4k

tokens

2,365

PP tok/s

23.4

TG tok/s

1732

TTFT (ms)

3.8

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.2.7

macOS macOS 15.7.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,810	23.9	3.5 GB	view
4k	2,365	23.4	3.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.9	1.00×
2×	33.7	1.41×
4×	64.6	2.70×