← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2

M3 Pro (14c) · 36 GB · 4bit · 2026-04-15

Performance

16k

tokens

65.7

PP tok/s

8.1

TG tok/s

249321

TTFT (ms)

17.8

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 36 GB

GPU Cores 14

Software

oMLX v0.3.4

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	74.0	8.7	15.9 GB	view
4k	73.8	8.7	17.1 GB	view
8k	71.2	8.5	17.4 GB	view
16k	65.7	8.1	17.8 GB	current