← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M1 Max (24c) · 64 GB · 4bit · 2026-05-18
Performance
16k
tokens
61.3
PP tok/s
11.6
TG tok/s
267277
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 61.8 12.6 16.7 GB view
4k 63.2 12.4 18.2 GB view
8k 62.8 10.9 19.2 GB view
16k 61.3 11.6 20.7 GB current
32k 60.1 10.7 23.7 GB view
64k 54.6 8.1 29.7 GB view