← Back to community benchmarks
Qwen3.6-27B-MTPLX-Optimized-Speed
Performance
1k
tokens
243.5
PP tok/s
29.1
TG tok/s
4205
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 243.5 | 29.1 | 15.8 GB | current |
| 4k | 246.3 | 28.1 | 17.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.1 | 1.00× |
| 2× | 53.0 | 1.82× |
| 4× | 59.0 | 2.03× |