← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
32k
tokens
112.3
PP tok/s
9.7
TG tok/s
291920
TTFT (ms)
29.6
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 118.7 | 10.9 | 22.6 GB | view |
| 4k | 119.8 | 10.8 | 24.0 GB | view |
| 8k | 115.4 | 10.7 | 25.1 GB | view |
| 16k | 117.0 | 10.4 | 26.6 GB | view |
| 32k | 112.3 | 9.7 | 29.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.9 | 1.00× |
| 2× | 17.9 | 1.64× |
| 4× | 18.9 | 1.73× |