← Back to community benchmarks

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

M3 Max (40c) · 64 GB · 6bit · 2026-04-19

Performance

4k

tokens

196.1

PP tok/s

14.7

TG tok/s

20888

TTFT (ms)

23.5

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	196.1	14.7	23.5 GB	current
8k	175.1	15.2	24.2 GB	view
16k	170.9	12.8	25.4 GB	view
32k	115.5	6.3	27.9 GB	view
64k	115.3	6.1	32.9 GB	view