← Back to community benchmarks
Qwen3.6-27B
Performance
64k
tokens
518.2
PP tok/s
22.3
TG tok/s
126470
TTFT (ms)
29.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 650.6 | 31.3 | 16.4 GB | view |
| 4k | 769.4 | 30.8 | 17.9 GB | view |
| 8k | 785.5 | 30.2 | 18.9 GB | view |
| 16k | 738.2 | 28.2 | 20.4 GB | view |
| 32k | 646.7 | 1.6 | 26.7 GB | view |
| 64k | 518.2 | 22.3 | 29.4 GB | current |
| 128k | 380.7 | 17.4 | 41.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.3 | 1.00× |
| 2× | 46.2 | 1.48× |