← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
99.9
PP tok/s
8.7
TG tok/s
10248
TTFT (ms)
15.3
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.4.1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 99.9 | 8.7 | 15.3 GB | current |
| 4k | 83.5 | 9.2 | 16.3 GB | view |
| 8k | 120.1 | 13.8 | 18.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.7 | 1.00× |
| 2× | 22.9 | 2.63× |
| 4× | 31.2 | 3.59× |
| 8× | 35.0 | 4.02× |