← Back to community benchmarks

Qwen3.6-27B-oQ4

M5 Max (40c) · 64 GB · 4bit · 2026-04-24
Performance
32k
tokens
661.2
PP tok/s
24.0
TG tok/s
49561
TTFT (ms)
22.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8.dev1
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 809.0 109.6 20.1 GB view
16k 766.5 28.2 19.7 GB view
32k 661.2 24.0 22.2 GB current