← Back to community benchmarks
Qwen3.6-27B
Performance
8k
tokens
743.3
PP tok/s
22.5
TG tok/s
11022
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.0
macOS
macOS 26.5.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 711.9 | 23.2 | 22.1 GB | view |
| 4k | 779.1 | 22.6 | 23.4 GB | view |
| 8k | 743.3 | 22.5 | 24.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.2 | 1.00× |
| 2× | 37.6 | 1.62× |
| 4× | 46.1 | 1.99× |
| 8× | 48.5 | 2.09× |