← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
8k
tokens
87.5
PP tok/s
17.3
TG tok/s
93618
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 85.7 | 18.1 | 15.8 GB | view |
| 4k | 87.8 | 17.2 | 17.3 GB | view |
| 8k | 87.5 | 17.3 | 18.3 GB | current |
| 16k | 86.1 | 15.6 | 19.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.1 | 1.00× |
| 2× | 21.5 | 1.19× |
| 4× | 23.5 | 1.30× |
| 8× | 47.2 | 2.61× |