← Back to community benchmarks
Qwen3.6-27B-mtp
Performance
1k
tokens
717.1
PP tok/s
28.3
TG tok/s
1428
TTFT (ms)
37.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
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 | 717.1 | 28.3 | 37.2 GB | current |
| 4k | 836.6 | 29.5 | 38.7 GB | view |
| 8k | 777.7 | 27.7 | 39.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.3 | 1.00× |
| 2× | 34.2 | 1.21× |
| 4× | 45.9 | 1.62× |