← Back to community benchmarks

Qwen3.5-9B

M2 (8c) · 16 GB · 4bit · 2026-03-10

Performance

4k

tokens

87.2

PP tok/s

17.0

TG tok/s

46963

TTFT (ms)

6.8

Peak mem (GB)

Hardware

Chip M2 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	88.2	16.9	6.5 GB	view
4k	87.2	17.0	6.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	16.9	1.00×
2×	13.5	0.80×
4×	16.8	0.99×