← Back to community benchmarks
Qwen3.6-27B-UD
Performance
128k
tokens
401.1
PP tok/s
15.7
TG tok/s
326768
TTFT (ms)
46.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 580.5 | 21.7 | 25.2 GB | view |
| 4k | 724.4 | 21.1 | 26.6 GB | view |
| 8k | 726.4 | 21.5 | 27.3 GB | view |
| 16k | 689.9 | 20.2 | 28.5 GB | view |
| 32k | 653.9 | 20.1 | 31.0 GB | view |
| 64k | 546.6 | 18.5 | 36.1 GB | view |
| 128k | 401.1 | 15.7 | 46.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.7 | 1.00× |
| 2× | 24.3 | 1.12× |
| 4× | 40.1 | 1.85× |