← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
32k
tokens
408.6
PP tok/s
21.4
TG tok/s
80192
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 429.6 | 26.7 | 16.8 GB | view |
| 4k | 469.3 | 25.6 | 18.2 GB | view |
| 8k | 453.5 | 24.9 | 19.2 GB | view |
| 16k | 434.2 | 23.9 | 20.7 GB | view |
| 32k | 408.6 | 21.4 | 23.7 GB | current |
| 64k | 339.6 | 17.5 | 29.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.7 | 1.00× |
| 2× | 24.3 | 0.91× |
| 4× | 41.3 | 1.55× |