← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
452.2
PP tok/s
24.7
TG tok/s
18118
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 423.9 | 26.6 | 16.8 GB | view |
| 4k | 465.8 | 25.6 | 18.2 GB | view |
| 8k | 452.2 | 24.7 | 19.2 GB | current |
| 16k | 402.2 | 23.4 | 20.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.6 | 1.00× |
| 2× | 52.7 | 1.98× |
| 4× | 90.7 | 3.41× |