← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
184.3
PP tok/s
21.8
TG tok/s
22226
TTFT (ms)
17.9
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 | 230.0 | 25.6 | 16.4 GB | view |
| 4k | 184.3 | 21.8 | 17.9 GB | current |
| 8k | 172.7 | 19.8 | 18.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.6 | 1.00× |
| 2× | 34.2 | 1.34× |
| 4× | 37.7 | 1.47× |
| 8× | 36.7 | 1.43× |