← Back to community benchmarks
Qwen3.6-27B
Performance
8k
tokens
99.7
PP tok/s
14.5
TG tok/s
82204
TTFT (ms)
17.9
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 100.5 | 15.2 | 15.8 GB | view |
| 4k | 97.3 | 14.9 | 17.3 GB | view |
| 8k | 99.7 | 14.5 | 17.9 GB | current |
| 16k | 97.2 | 9.8 | 19.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.2 | 1.00× |
| 2× | 25.5 | 1.68× |