← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M3 Max (40c) · 128 GB · 8bit · 2026-05-17

Performance

1k

tokens

204.5

PP tok/s

20.5

TG tok/s

5007

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	204.5	20.5	28.8 GB	current
4k	203.6	20.1	30.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	20.5	1.00×
2×	24.1	1.18×
4×	31.8	1.55×