← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
4k
tokens
470.8
PP tok/s
17.7
TG tok/s
8700
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.3.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 431.0 | 18.2 | 15.8 GB | view |
| 4k | 470.8 | 17.7 | 17.3 GB | current |