← Back to community benchmarks
Qwen3.6-27B
Performance
4k
tokens
130.9
PP tok/s
9.7
TG tok/s
31284
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.0
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 129.2 | 9.9 | 28.3 GB | view |
| 4k | 130.9 | 9.7 | 29.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.9 | 1.00× |
| 2× | 18.2 | 1.84× |
| 4× | 27.8 | 2.81× |
| 8× | 33.1 | 3.34× |