← Back to community benchmarks
Qwen3.6-27B-oQ6-mtp
Performance
16k
tokens
709.9
PP tok/s
23.3
TG tok/s
23078
TTFT (ms)
28.0
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 27.0
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 664.2 | 24.7 | 24.7 GB | view |
| 4k | 788.1 | 23.3 | 26.2 GB | view |
| 8k | 735.2 | 24.0 | 26.8 GB | view |
| 16k | 709.9 | 23.3 | 28.0 GB | current |
| 32k | 663.4 | 22.1 | 30.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.7 | 1.00× |
| 2× | 38.0 | 1.54× |
| 4× | 47.0 | 1.90× |