← Back to community benchmarks

Qwen3.5-0.8B

M1 (7c) · 16 GB · 4bit · 2026-03-09

Performance

16k

tokens

647.6

PP tok/s

68.2

TG tok/s

25298

TTFT (ms)

2.0

Peak mem (GB)

Hardware

Chip M1 (7c)

Memory 16 GB

GPU Cores 7

Software

oMLX v0.2.6

macOS macOS 15.7.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	756.4	100.8	1.5 GB	view
4k	734.1	91.3	1.6 GB	view
8k	710.7	82.2	1.6 GB	view
16k	647.6	68.2	2.0 GB	current
32k	552.2	47.8	2.6 GB	view
64k	408.6	17.3	4.1 GB	view