← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
785.2
PP tok/s
32.1
TG tok/s
1304
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 785.2 | 32.1 | 15.8 GB | current |
| 4k | 866.0 | 31.4 | 17.3 GB | view |
| 8k | 787.4 | 29.9 | 18.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 32.1 | 1.00× |
| 2× | 56.9 | 1.77× |
| 4× | 73.3 | 2.28× |