← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
8k
tokens
141.7
PP tok/s
16.3
TG tok/s
57824
TTFT (ms)
25.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.2
Context
8,192