← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
174.4
PP tok/s
32.9
TG tok/s
5870
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
64 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 174.4 | 32.9 | 15.8 GB | current |
| 4k | 182.1 | 31.4 | 17.3 GB | view |