← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
1k
tokens
231.6
PP tok/s
24.8
TG tok/s
4422
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 231.6 | 24.8 | 23.0 GB | current |
| 4k | 240.6 | 27.7 | 24.4 GB | view |
| 8k | 239.9 | 27.0 | 25.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.8 | 1.00× |
| 2× | 34.0 | 1.37× |
| 4× | 36.8 | 1.48× |