← Back to community benchmarks

ThinkingCap-Qwen3.6-27B

M1 Max (32c) · 64 GB · 6bit · 2026-07-25

Performance

64k

tokens

67.6

PP tok/s

10.6

TG tok/s

968814

TTFT (ms)

30.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.5.3

macOS macOS 26.5.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	92.5	13.7	23.4 GB	view
16k	88.6	13.0	25.1 GB	view
64k	67.6	10.6	30.2 GB	current
128k	51.4	8.6	37.4 GB	view