← Back to community benchmarks

Qwen3.5-0.8B

M1 (5c) · 8 GB · 8bit · 2026-03-19

Performance

4k

tokens

974.4

PP tok/s

48.4

TG tok/s

4204

TTFT (ms)

2.3

Peak mem (GB)

Hardware

Chip M1 (5c)

Memory 8 GB

GPU Cores 5

Software

oMLX v0.2.18

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,042	58.1	1.6 GB	view
4k	974.4	48.4	2.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.1	1.00×
2×	48.2	0.83×
4×	119.4	2.06×