← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
189.1
PP tok/s
22.5
TG tok/s
5416
TTFT (ms)
15.1
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 | 189.1 | 22.5 | 15.1 GB | current |
| 4k | 195.6 | 21.7 | 16.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.5 | 1.00× |
| 2× | 43.1 | 1.92× |
| 4× | 51.1 | 2.27× |
| 8× | 45.8 | 2.04× |