← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 64 GB · 4bit · 2026-06-19
Performance
16k
tokens
667.9
PP tok/s
30.0
TG tok/s
24531
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 847.8 32.5 17.9 GB view
16k 667.9 30.0 20.2 GB current