← Back to community benchmarks

Qwen3.6-27BoQ5

M1 Max (32c) · 32 GB · 5bit · 2026-04-25

Performance

4k

tokens

114.4

PP tok/s

15.9

TG tok/s

35797

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.6

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	60.7	23.2	25.1 GB	view
4k	114.4	15.9	21.0 GB	current
8k	142.6	15.3	21.6 GB	view