← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
32k
tokens
1,603
PP tok/s
24.0
TG tok/s
20445
TTFT (ms)
39.0
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 1,603 | 24.0 | 39.0 GB | current |
| 64k | 1,195 | 22.6 | 40.9 GB | view |