← Back to community benchmarks
Qwen3.6-27B-oQ4
Performance
8k
tokens
860.2
PP tok/s
30.2
TG tok/s
9524
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 784.9 | 28.4 | 16.4 GB | view |
| 4k | 910.3 | 29.9 | 17.8 GB | view |
| 8k | 860.2 | 30.2 | 18.9 GB | current |
| 16k | 746.6 | 15.8 | 20.4 GB | view |
| 32k | 678.8 | 10.4 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.4 | 1.00× |
| 2× | 24.5 | 0.86× |
| 4× | 46.5 | 1.64× |
| 8× | 37.1 | 1.31× |