← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
4k
tokens
360.2
PP tok/s
14.9
TG tok/s
11371
TTFT (ms)
20.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 27.0
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 322.1 | 15.0 | 19.2 GB | view |
| 4k | 360.2 | 14.9 | 20.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.0 | 1.00× |
| 2× | 24.9 | 1.66× |
| 4× | 32.2 | 2.15× |
| 8× | 35.5 | 2.37× |