← Back to community benchmarks

Qwen3.5-9B

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

Performance

1k

tokens

1,108

PP tok/s

68.4

TG tok/s

924

TTFT (ms)

10.7

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.2.6

macOS macOS 15.3

Context 1,024

Performance by Context Length

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

Batching Results

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