← Back to community benchmarks
Qwen3.6-27B-MXFP4-MTP
Performance
8k
tokens
87.5
PP tok/s
11.4
TG tok/s
93592
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.4.0
macOS
macOS 26.5
Context
8,192