← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Distilled

M3 Pro (18c) · 36 GB · 4bit · 2026-03-16

Performance

8k

tokens

96.7

PP tok/s

8.3

TG tok/s

84720

TTFT (ms)

16.6

Peak mem (GB)

Hardware

Chip M3 Pro (18c)

Memory 36 GB

GPU Cores 18

Software

oMLX v0.2.12

macOS macOS 26.2

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	96.6	8.8	15.8 GB	view
4k	98.2	8.6	16.1 GB	view
8k	96.7	8.3	16.6 GB	current
16k	93.3	7.1	17.5 GB	view