← Back to community benchmarks
Qwen3.6-27B-OptiQ
Performance
1k
tokens
771.7
PP tok/s
27.3
TG tok/s
1327
TTFT (ms)
36.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 771.7 | 27.3 | 36.8 GB | current |
| 4k | 772.9 | 26.6 | 38.2 GB | view |
| 8k | 627.8 | 25.8 | 39.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.3 | 1.00× |
| 2× | 44.9 | 1.64× |
| 4× | 58.4 | 2.14× |