← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
64k
tokens
323.3
PP tok/s
17.5
TG tok/s
202696
TTFT (ms)
27.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
65,536