← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
61.2
PP tok/s
5.8
TG tok/s
16732
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.9
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 61.2 | 5.8 | 15.8 GB | current |
| 4k | 56.4 | 5.7 | 17.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.8 | 1.00× |
| 2× | 11.5 | 1.98× |
| 4× | 15.4 | 2.66× |
| 8× | 16.1 | 2.78× |