← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled

M5 Pro (20c) · 48 GB · 6bit · 2026-04-24

Performance

4k

tokens

2,066

PP tok/s

73.3

TG tok/s

1983

TTFT (ms)

28.1

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.7rc2

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,417	76.5	27.3 GB	view
4k	2,066	73.3	28.1 GB	current
8k	2,143	70.0	28.4 GB	view
16k	2,034	63.2	29.1 GB	view