← Back to community benchmarks

Qwen3.5-9Bbf16 18b

M2 Pro (19c) · 32 GB · bf16 · 2026-03-11

Performance

1k

tokens

319.6

PP tok/s

10.6

TG tok/s

3204

TTFT (ms)

18.3

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 32 GB

GPU Cores 19

Software

oMLX v0.2.8

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	319.6	10.6	18.3 GB	current
4k	335.2	10.5	18.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	10.6	1.00×
2×	10.2	0.96×
4×	19.7	1.86×