← Back to community benchmarks
Qwen3.6-27B-Opus4.6-Reasoning
Performance
32k
tokens
114.7
PP tok/s
13.0
TG tok/s
285660
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 124.0 | 15.6 | 15.8 GB | view |
| 4k | 125.7 | 15.2 | 17.3 GB | view |
| 8k | 125.1 | 14.9 | 18.3 GB | view |
| 16k | 121.6 | 14.1 | 19.8 GB | view |
| 32k | 114.7 | 13.0 | 22.8 GB | current |
| 64k | 101.8 | 11.0 | 28.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.6 | 1.00× |
| 2× | 29.5 | 1.89× |