← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
1k
tokens
412.2
PP tok/s
23.8
TG tok/s
2484
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 412.2 | 23.8 | 16.7 GB | current |
| 4k | 437.4 | 25.3 | 18.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.8 | 1.00× |
| 2× | 27.3 | 1.15× |
| 4× | 29.5 | 1.24× |