← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 64 GB · 4bit · 2026-07-24
Performance
64k
tokens
465.0
PP tok/s
19.3
TG tok/s
140947
TTFT (ms)
29.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.4
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 724.5 27.9 19.8 GB view
32k 608.5 24.7 23.4 GB view
64k 465.0 19.3 29.4 GB current