← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
16k
tokens
749.6
PP tok/s
26.9
TG tok/s
21856
TTFT (ms)
32.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 721.6 | 29.5 | 28.8 GB | view |
| 4k | 823.9 | 29.5 | 30.3 GB | view |
| 8k | 798.5 | 29.0 | 30.9 GB | view |
| 16k | 749.6 | 26.9 | 32.1 GB | current |
| 32k | 697.5 | 25.7 | 34.6 GB | view |
| 64k | 580.9 | 22.2 | 39.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.5 | 1.00× |
| 2× | 34.3 | 1.16× |
| 4× | 49.0 | 1.66× |