← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized
Performance
4k
tokens
207.3
PP tok/s
23.8
TG tok/s
19761
TTFT (ms)
21.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096