← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 4bit · 2026-06-04

Performance

4k

tokens

251.1

PP tok/s

27.8

TG tok/s

16315

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.1

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	243.2	28.3	15.8 GB	view
4k	251.1	27.8	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.3	1.00×
2×	54.1	1.91×
4×	62.7	2.22×