← Back to community benchmarks
Qwen3.6-27B4bit-MTP
Performance
4k
tokens
242.7
PP tok/s
43.1
TG tok/s
16875
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 229.9 | 40.7 | 16.1 GB | view |
| 4k | 242.7 | 43.1 | 17.5 GB | current |
| 8k | 238.4 | 41.3 | 18.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.7 | 1.00× |
| 2× | 53.7 | 1.32× |
| 4× | 59.8 | 1.47× |