← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
209.2
PP tok/s
22.6
TG tok/s
4895
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 209.2 | 22.6 | 15.8 GB | current |
| 4k | 212.6 | 21.9 | 17.3 GB | view |