← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
281.9
PP tok/s
16.0
TG tok/s
3632
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 281.9 | 16.0 | 15.8 GB | current |
| 4k | 305.5 | 15.6 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.0 | 1.00× |
| 2× | 25.2 | 1.57× |