← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
64k
tokens
316.7
PP tok/s
9.3
TG tok/s
206948
TTFT (ms)
29.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 425.4 | 16.6 | 16.5 GB | view |
| 4k | 470.3 | 16.3 | 17.9 GB | view |
| 32k | 390.6 | 9.1 | 22.3 GB | view |
| 64k | 316.7 | 9.3 | 29.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 16.6 | 1.00× |
| 2× | 19.7 | 1.19× |
| 4× | 33.7 | 2.03× |