← Back to community benchmarks
Youssofal--Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
432.9
PP tok/s
17.7
TG tok/s
2365
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
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 | 432.9 | 17.7 | 15.8 GB | current |
| 4k | 459.9 | 17.3 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.7 | 1.00× |
| 2× | 32.2 | 1.82× |
| 4× | 43.3 | 2.45× |