← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
64k
tokens
582.0
PP tok/s
15.5
TG tok/s
112598
TTFT (ms)
39.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 703.1 | 18.2 | 28.3 GB | view |
| 4k | 840.5 | 18.1 | 29.8 GB | view |
| 8k | 820.9 | 17.8 | 30.4 GB | view |
| 16k | 776.8 | 17.1 | 31.7 GB | view |
| 32k | 703.3 | 16.6 | 34.2 GB | view |
| 64k | 582.0 | 15.5 | 39.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.2 | 1.00× |
| 2× | 34.3 | 1.88× |
| 4× | 49.0 | 2.69× |