← Back to community benchmarks

Qwen3.5-9B

M1 (7c) · 16 GB · 8bit · 2026-04-26

Performance

1k

tokens

67.9

PP tok/s

7.0

TG tok/s

15090

TTFT (ms)

9.8

Peak mem (GB)

Hardware

Chip M1 (7c)

Memory 16 GB

GPU Cores 7

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	7.0	1.00×
2×	13.5	1.93×
4×	17.5	2.50×