← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
8k
tokens
248.4
PP tok/s
27.6
TG tok/s
32980
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 243.0 | 29.3 | 15.8 GB | view |
| 4k | 250.8 | 28.3 | 17.3 GB | view |
| 8k | 248.4 | 27.6 | 18.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.3 | 1.00× |
| 2× | 54.6 | 1.86× |
| 4× | 62.4 | 2.13× |