← Back to community benchmarks

Qwen3.5-9B

M3 Ultra (60c) · 96 GB · 8bit · 2026-03-10

Performance

4k

tokens

1,120

PP tok/s

65.9

TG tok/s

3659

TTFT (ms)

11.0

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.2.6

macOS macOS 15.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,108	68.4	10.7 GB	view
4k	1,120	65.9	11.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	68.4	1.00×
2×	115.6	1.69×
4×	147.0	2.15×