← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
206.7
PP tok/s
6.3
TG tok/s
19820
TTFT (ms)
17.8
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 200.9 | 6.6 | 16.4 GB | view |
| 4k | 206.7 | 6.3 | 17.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.6 | 1.00× |
| 2× | 7.5 | 1.14× |
| 4× | 10.9 | 1.65× |