← Back to community benchmarks

Qwen3.5-0.8B

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

Performance

4k

tokens

2,078

PP tok/s

23.3

TG tok/s

1971

TTFT (ms)

3.8

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 16 GB

GPU Cores 19

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	1,673	24.1	3.5 GB	view
4k	2,078	23.3	3.8 GB	current

Batching Results

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