← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
350.4
PP tok/s
17.9
TG tok/s
2922
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.4.4rc2
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 350.4 | 17.9 | 15.8 GB | current |
| 4k | 385.2 | 17.6 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.9 | 1.00× |
| 2× | 29.4 | 1.64× |
| 4× | 36.3 | 2.03× |