← Back to community benchmarks

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

M5 Pro (20c) · 48 GB · 4bit · 2026-03-19

Performance

8k

tokens

460.0

PP tok/s

16.9

TG tok/s

17807

TTFT (ms)

18.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	424.6	17.9	15.8 GB	view
4k	463.2	17.5	17.4 GB	view
8k	460.0	16.9	18.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.9	1.00×
2×	32.3	1.80×
4×	43.7	2.44×
8×	46.8	2.61×