← Back to community benchmarks

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

M3 Max (30c) · 36 GB · 6bit · 2026-03-23

Performance

4k

tokens

149.1

PP tok/s

11.9

TG tok/s

27468

TTFT (ms)

23.6

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.2.19

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	149.5	12.2	22.1 GB	view
4k	149.1	11.9	23.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.2	1.00×
2×	20.1	1.65×
4×	19.8	1.62×