← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
32k
tokens
399.0
PP tok/s
21.5
TG tok/s
82115
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
32,768