← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
107.9
PP tok/s
18.3
TG tok/s
9489
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024