← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
63.1
PP tok/s
6.6
TG tok/s
16240
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 63.1 | 6.6 | 15.8 GB | current |
| 32k | 54.0 | 5.5 | 21.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.6 | 1.00× |
| 2× | 13.1 | 1.98× |