← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
4k
tokens
52.2
PP tok/s
6.3
TG tok/s
78482
TTFT (ms)
17.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.10
macOS
macOS 15.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 54.7 | 6.6 | 15.8 GB | view |
| 4k | 52.2 | 6.3 | 17.2 GB | current |