← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
1k
tokens
728.8
PP tok/s
24.0
TG tok/s
1405
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M5 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 | 728.8 | 24.0 | 22.8 GB | current |
| 4k | 828.6 | 23.6 | 24.3 GB | view |
| 8k | 785.5 | 23.4 | 25.3 GB | view |
| 16k | 756.8 | 22.5 | 26.8 GB | view |
| 32k | 695.8 | 21.0 | 29.8 GB | view |
| 64k | 587.4 | 18.9 | 35.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.0 | 1.00× |
| 2× | 37.1 | 1.55× |
| 4× | 47.6 | 1.98× |