← Back to community benchmarks

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled

M3 (10c) · 24 GB · 6bit · 2026-03-23

Performance

1k

tokens

169.9

PP tok/s

13.4

TG tok/s

6029

TTFT (ms)

7.8

Peak mem (GB)

Hardware

Chip M3 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	169.9	13.4	7.8 GB	current
4k	157.6	12.0	8.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	13.4	1.00×
2×	9.8	0.73×
4×	13.4	1.00×