← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-04-18

Performance

1k

tokens

76.3

PP tok/s

12.2

TG tok/s

13414

TTFT (ms)

6.3

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.2	1.00×
2×	18.8	1.54×
4×	19.3	1.58×