← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
132.9
PP tok/s
22.8
TG tok/s
7704
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 132.9 | 22.8 | 16.7 GB | current |
| 4k | 135.3 | 20.2 | 18.2 GB | view |