← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
239.5
PP tok/s
30.2
TG tok/s
4275
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.4.4rc1
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 239.5 | 30.2 | 15.8 GB | current |
| 4k | 249.3 | 29.1 | 17.3 GB | view |