← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
47.4
PP tok/s
9.7
TG tok/s
21605
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.9rc1
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 47.4 | 9.7 | 16.7 GB | current |
| 4k | 47.8 | 10.2 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.7 | 1.00× |
| 2× | 11.9 | 1.23× |
| 4× | 12.3 | 1.27× |