← Back to community benchmarks

Qwen3.5-0.8B

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

Performance

1k

tokens

1,735

PP tok/s

23.9

TG tok/s

590

TTFT (ms)

3.5

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 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,735	23.9	3.5 GB	current
4k	2,342	23.3	3.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.9	1.00×
2×	37.6	1.57×
4×	73.8	3.09×