← Back to community benchmarks
Qwen3.6-27B-oQ8-mtp
Performance
8k
tokens
634.3
PP tok/s
16.9
TG tok/s
12916
TTFT (ms)
30.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 693.1 | 17.8 | 28.3 GB | view |
| 4k | 694.2 | 17.4 | 29.8 GB | view |
| 8k | 634.3 | 16.9 | 30.8 GB | current |
| 16k | 573.5 | 16.2 | 32.3 GB | view |
| 32k | 506.7 | 15.2 | 35.3 GB | view |
| 64k | 337.2 | 12.3 | 41.4 GB | view |
| 128k | 267.2 | 10.9 | 53.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.8 | 1.00× |
| 2× | 26.4 | 1.48× |
| 4× | 33.8 | 1.90× |