← Back to community benchmarks
Qwen3.6-27B
Performance
8k
tokens
318.3
PP tok/s
15.7
TG tok/s
25740
TTFT (ms)
65.6
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.4
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 299.6 | 12.0 | 62.4 GB | view |
| 4k | 319.4 | 16.1 | 65.0 GB | view |
| 8k | 318.3 | 15.7 | 65.6 GB | current |
| 16k | 310.1 | 19.6 | 66.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.0 | 1.00× |
| 2× | 39.2 | 3.27× |
| 4× | 41.0 | 3.42× |
| 8× | 52.9 | 4.41× |