← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
32k
tokens
407.7
PP tok/s
21.6
TG tok/s
80371
TTFT (ms)
22.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 421.3 | 25.5 | 16.8 GB | view |
| 32k | 407.7 | 21.6 | 22.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.5 | 1.00× |
| 2× | 31.2 | 1.22× |
| 4× | 41.4 | 1.62× |