← Back to community benchmarks
ThinkingCap-Qwen3.6-27B-OptiQ
Performance
8k
tokens
419.5
PP tok/s
13.9
TG tok/s
19526
TTFT (ms)
21.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 400.0 | 14.2 | 19.2 GB | view |
| 4k | 439.8 | 14.2 | 20.6 GB | view |
| 8k | 419.5 | 13.9 | 21.7 GB | current |
| 16k | 409.1 | 13.4 | 23.2 GB | view |
| 32k | 234.4 | 12.7 | 25.0 GB | view |
| 64k | 242.5 | 11.3 | 25.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.2 | 1.00× |
| 2× | 25.2 | 1.77× |
| 4× | 35.9 | 2.53× |