← Back to community benchmarks
Qwen3.6-27B-mtp
Performance
4k
tokens
230.4
PP tok/s
20.7
TG tok/s
17780
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 217.4 | 21.2 | 28.3 GB | view |
| 4k | 230.4 | 20.7 | 29.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.2 | 1.00× |
| 2× | 37.5 | 1.77× |
| 4× | 51.4 | 2.42× |