← Back to community benchmarks

Qwen3.5-9B

M3 Pro (14c) · 18 GB · 4bit · 2026-03-14

Performance

8k

tokens

267.3

PP tok/s

24.5

TG tok/s

30644

TTFT (ms)

7.1

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 18 GB

GPU Cores 14

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	270.6	26.1	6.7 GB	view
4k	273.7	25.8	7.0 GB	view
8k	267.3	24.5	7.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	26.1	1.00×
2×	53.8	2.06×
4×	64.6	2.48×