← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
16k
tokens
447.3
PP tok/s
23.9
TG tok/s
36626
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 433.8 | 26.3 | 16.7 GB | view |
| 4k | 474.4 | 26.5 | 18.2 GB | view |
| 8k | 469.7 | 25.4 | 19.2 GB | view |
| 16k | 447.3 | 23.9 | 20.7 GB | current |
| 32k | 407.0 | 21.8 | 23.7 GB | view |
| 64k | 339.6 | 18.2 | 29.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.3 | 1.00× |
| 2× | 31.6 | 1.20× |
| 4× | 41.9 | 1.59× |
| 8× | 44.9 | 1.71× |