← Back to community benchmarks
Qwen3.6-27B-oQ6
Performance
32k
tokens
478.0
PP tok/s
13.7
TG tok/s
68552
TTFT (ms)
29.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 411.4 | 17.6 | 22.6 GB | view |
| 4k | 522.2 | 17.9 | 24.0 GB | view |
| 8k | 554.1 | 17.9 | 25.1 GB | view |
| 16k | 539.2 | 17.0 | 26.6 GB | view |
| 32k | 478.0 | 13.7 | 29.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.6 | 1.00× |
| 2× | 22.2 | 1.26× |
| 4× | 26.7 | 1.52× |