← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
32k
tokens
392.2
PP tok/s
16.7
TG tok/s
83550
TTFT (ms)
29.9
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 399.2 | 19.8 | 23.0 GB | view |
| 4k | 442.4 | 19.3 | 24.4 GB | view |
| 8k | 431.1 | 18.8 | 25.4 GB | view |
| 16k | 427.0 | 17.4 | 26.9 GB | view |
| 32k | 392.2 | 16.7 | 29.9 GB | current |
| 64k | 324.6 | 14.2 | 36.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.8 | 1.00× |
| 2× | 22.8 | 1.15× |
| 4× | 28.8 | 1.45× |