← Back to community benchmarks

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

M1 Max (24c) · 32 GB · 4bit · 2026-03-12

Performance

4k

tokens

64.8

PP tok/s

14.7

TG tok/s

63164

TTFT (ms)

16.1

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.2.8

macOS macOS 15.7.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	63.7	15.4	15.8 GB	view
4k	64.8	14.7	16.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.4	1.00×
2×	16.7	1.08×
4×	17.4	1.13×