← Back to community benchmarks

Qwen3.5-27B

M3 Max (40c) · 64 GB · 6bit · 2026-03-12

Performance

8k

tokens

163.7

PP tok/s

10.0

TG tok/s

50057

TTFT (ms)

23.7

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.2.9

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	211.0	16.3	22.9 GB	view
8k	163.7	10.0	23.7 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	16.3	1.00×
2×	16.7	1.02×
4×	4.5	0.28×