← Back to community benchmarks

Qwen3.5-27B

M2 Max (38c) · 96 GB · 4bit · 2026-03-23

Performance

1k

tokens

116.4

PP tok/s

20.9

TG tok/s

8799

TTFT (ms)

16.7

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.2.19

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	116.4	20.9	16.7 GB	current
4k	115.2	19.9	18.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	20.9	1.00×
2×	22.0	1.05×
4×	19.4	0.93×