← Back to community benchmarks
Qwen3.6-27B
Performance
16k
tokens
287.6
PP tok/s
8.2
TG tok/s
56958
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 47.8 | 11.1 | 16.6 GB | view |
| 4k | 49.0 | 11.0 | 18.0 GB | view |
| 8k | 49.1 | 10.5 | 18.6 GB | view |
| 16k | 287.6 | 8.2 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.1 | 1.00× |
| 2× | 13.0 | 1.17× |