← Back to community benchmarks
Qwen3.6-27B-mtp
Performance
1k
tokens
390.3
PP tok/s
13.6
TG tok/s
2624
TTFT (ms)
28.8
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 | 390.3 | 13.6 | 28.8 GB | current |
| 4k | 437.3 | 15.7 | 30.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.6 | 1.00× |
| 2× | 18.2 | 1.34× |
| 4× | 27.4 | 2.01× |