← Back to community benchmarks

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

M5 Pro (16c) · 24 GB · 4bit · 2026-06-15

Performance

1k

tokens

208.2

PP tok/s

18.5

TG tok/s

4917

TTFT (ms)

14.7

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.4.4rc1

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	208.2	18.5	14.7 GB	current
4k	180.1	17.6	14.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.5	1.00×
2×	36.2	1.96×
4×	73.5	3.97×