← Back to community benchmarks

Qwen3.5-0.8B

M2 (10c) · 8 GB · 8bit · 2026-03-19

Performance

1k

tokens

1,178

PP tok/s

88.1

TG tok/s

869

TTFT (ms)

1.9

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 8 GB

GPU Cores 10

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,178	88.1	1.9 GB	current
4k	1,177	81.2	2.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	88.1	1.00×
2×	158.2	1.80×
4×	215.6	2.45×