← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
4k
tokens
369.1
PP tok/s
15.0
TG tok/s
11097
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 | 305.1 | 14.8 | 19.2 GB | view |
| 4k | 369.1 | 15.0 | 20.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.8 | 1.00× |
| 2× | 25.5 | 1.72× |
| 4× | 32.3 | 2.18× |
| 8× | 35.8 | 2.42× |