← Back to community benchmarks
Qwen3.6-27B-mtp
Performance
4k
tokens
121.2
PP tok/s
8.0
TG tok/s
33799
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 119.4 | 8.4 | 28.3 GB | view |
| 4k | 121.2 | 8.0 | 29.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.4 | 1.00× |
| 2× | 62.5 | 7.44× |
| 4× | 31.1 | 3.70× |