← Back to community benchmarks

Qwen3.6-27B-oQ8-fp16-mtp

M1 Max (32c) · 64 GB · 8bit · 2026-05-10

Performance

32k

tokens

136.6

PP tok/s

14.5

TG tok/s

239912

TTFT (ms)

35.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	141.8	14.6	28.8 GB	view
4k	148.7	16.5	30.3 GB	view
8k	147.9	14.1	31.3 GB	view
16k	144.4	15.1	32.8 GB	view
32k	136.6	14.5	35.8 GB	current