← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
4k
tokens
438.5
PP tok/s
15.3
TG tok/s
9341
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 386.2 | 14.1 | 28.8 GB | view |
| 4k | 438.5 | 15.3 | 30.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.1 | 1.00× |
| 2× | 18.5 | 1.31× |
| 4× | 27.4 | 1.94× |