← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M5 Max (40c) · 64 GB · 6bit · 2026-05-15
Performance
4k
tokens
705.3
PP tok/s
30.7
TG tok/s
5807
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 740.5 32.9 23.0 GB view
4k 705.3 30.7 24.4 GB current
8k 646.3 28.1 25.4 GB view
16k 585.7 28.4 26.9 GB view