← Back to community benchmarks

Qwen3.5-9B

M3 (10c) · 16 GB · 4bit · 2026-03-09

Performance

4k

tokens

157.4

PP tok/s

17.6

TG tok/s

26026

TTFT (ms)

6.8

Peak mem (GB)

Hardware

Chip M3 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 15.7.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	174.7	17.7	6.5 GB	view
4k	157.4	17.6	6.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.7	1.00×
2×	13.9	0.79×
4×	17.2	0.97×