← Back to community benchmarks

Qwen3.5-0.8B

M2 Pro (19c) · 16 GB · unknown · 2026-03-10

Performance

1k

tokens

1,673

PP tok/s

24.1

TG tok/s

612

TTFT (ms)

3.5

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 16 GB

GPU Cores 19

Software

oMLX v0.2.6

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,673	24.1	3.5 GB	current
4k	2,078	23.3	3.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	24.1	1.00×
2×	36.2	1.50×
4×	76.3	3.17×