← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
32k
tokens
138.3
PP tok/s
16.6
TG tok/s
236963
TTFT (ms)
22.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
32,768