← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
395.4
PP tok/s
23.4
TG tok/s
2590
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 395.4 | 23.4 | 16.7 GB | current |
| 4k | 421.5 | 24.1 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.4 | 1.00× |
| 2× | 28.8 | 1.23× |
| 4× | 34.8 | 1.49× |