← Back to community benchmarks

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

M5 Pro (16c) · 48 GB · 4bit · 2026-06-19

Performance

1k

tokens

364.1

PP tok/s

18.4

TG tok/s

2812

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	364.1	18.4	15.8 GB	current
4k	391.5	18.1	17.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.4	1.00×
2×	29.9	1.62×
4×	35.5	1.93×
8×	37.0	2.01×