← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
16k
tokens
82.5
PP tok/s
12.9
TG tok/s
198507
TTFT (ms)
19.8
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 100.6 | 15.8 | 15.8 GB | view |
| 4k | 101.3 | 15.3 | 17.3 GB | view |
| 8k | 96.0 | 14.4 | 18.3 GB | view |
| 16k | 82.5 | 12.9 | 19.8 GB | current |
| 32k | 77.4 | 11.1 | 22.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.8 | 1.00× |
| 2× | 19.9 | 1.26× |
| 4× | 24.5 | 1.55× |