← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
8k
tokens
115.4
PP tok/s
13.6
TG tok/s
70976
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 122.9 | 14.9 | 15.8 GB | view |
| 4k | 122.8 | 14.3 | 17.3 GB | view |
| 8k | 115.4 | 13.6 | 18.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.9 | 1.00× |
| 2× | 23.4 | 1.57× |
| 4× | 27.4 | 1.84× |
| 8× | 24.0 | 1.61× |