← Back to community benchmarks

Qwen3.6-27B-OptiQ

M5 (10c) · 32 GB · 4bit · 2026-06-17

Performance

1k

tokens

214.4

PP tok/s

6.9

TG tok/s

4775

TTFT (ms)

19.1

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	214.4	6.9	19.1 GB	current
4k	217.7	6.8	20.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	6.9	1.00×
2×	14.2	2.06×
4×	20.5	2.97×