← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
4k
tokens
228.3
PP tok/s
7.7
TG tok/s
17940
TTFT (ms)
17.8
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 219.1 | 8.0 | 16.4 GB | view |
| 4k | 228.3 | 7.7 | 17.8 GB | current |
| 8k | 219.7 | 7.7 | 18.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.0 | 1.00× |
| 2× | 16.2 | 2.02× |
| 4× | 21.5 | 2.69× |