← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
403.3
PP tok/s
24.7
TG tok/s
2539
TTFT (ms)
16.8
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 403.3 | 24.7 | 16.8 GB | current |
| 4k | 434.2 | 24.2 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.7 | 1.00× |
| 2× | 29.1 | 1.18× |
| 4× | 35.7 | 1.45× |