← Back to community benchmarks

Qwen3.5-0.8B-OptiQ

M1 (8c) · 16 GB · 4bit · 2026-03-12

Performance

1k

tokens

618.2

PP tok/s

67.1

TG tok/s

1657

TTFT (ms)

1.6

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.9

macOS macOS 15.7.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	618.2	67.1	1.6 GB	current
4k	751.4	63.5	1.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	67.1	1.00×
2×	120.2	1.79×
4×	152.9	2.28×