← Back to community benchmarks

Qwen3.5-0.8B

M1 (7c) · 16 GB · 8bit · 2026-03-09

Performance

64k

tokens

414.9

PP tok/s

24.8

TG tok/s

157966

TTFT (ms)

4.4

Peak mem (GB)

Hardware

Chip M1 (7c)

Memory 16 GB

GPU Cores 7

Software

oMLX v0.2.6

macOS macOS 15.7.4

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	755.9	62.4	1.8 GB	view
4k	733.9	58.9	1.9 GB	view
8k	714.0	55.0	2.0 GB	view
16k	654.9	47.9	2.4 GB	view
32k	554.7	37.3	3.0 GB	view
64k	414.9	24.8	4.4 GB	current