← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 16 GB · 4bit · 2026-04-28

Performance

1k

tokens

189.4

PP tok/s

21.3

TG tok/s

5407

TTFT (ms)

5.7

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.3.8.dev3

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	189.4	21.3	5.7 GB	current
4k	193.7	19.2	6.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	21.3	1.00×
2×	41.0	1.92×
4×	46.5	2.18×