← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
205.0
PP tok/s
5.7
TG tok/s
39952
TTFT (ms)
18.8
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 215.7 | 7.6 | 16.4 GB | view |
| 4k | 219.0 | 6.3 | 17.8 GB | view |
| 8k | 205.0 | 5.7 | 18.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.6 | 1.00× |
| 2× | 149.0 | 19.61× |
| 4× | 14.1 | 1.86× |