← Back to community benchmarks

Qwen3.6-27BoQ5

M5 Max (32c) · 36 GB · 5bit · 2026-05-19

Performance

4k

tokens

654.9

PP tok/s

20.2

TG tok/s

6254

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M5 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	629.5	20.8	19.6 GB	view
4k	654.9	20.2	21.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	20.8	1.00×
2×	34.0	1.63×
4×	40.5	1.95×