← Back to community benchmarks
Qwen3.6-27B
Performance
1k
tokens
347.8
PP tok/s
17.1
TG tok/s
2944
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 347.8 | 17.1 | 15.8 GB | current |
| 4k | 378.5 | 17.1 | 17.3 GB | view |
| 16k | 347.9 | 15.5 | 19.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.1 | 1.00× |
| 2× | 26.5 | 1.55× |
| 4× | 31.9 | 1.87× |