← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
1k
tokens
393.9
PP tok/s
9.9
TG tok/s
2600
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 393.9 | 9.9 | 28.3 GB | current |
| 4k | 441.1 | 9.7 | 29.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.9 | 1.00× |
| 2× | 18.5 | 1.87× |
| 4× | 25.0 | 2.53× |