← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Max (30c) · 64 GB · 4bit · 2026-06-03
Performance
16k
tokens
89.5
PP tok/s
16.4
TG tok/s
183012
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.4.1
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 89.7 17.1 18.1 GB view
16k 89.5 16.4 20.5 GB current