← Back to community benchmarks
Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16
Performance
32k
tokens
644.9
PP tok/s
17.2
TG tok/s
50810
TTFT (ms)
34.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 713.4 | 18.8 | 28.3 GB | view |
| 4k | 852.6 | 18.5 | 29.8 GB | view |
| 8k | 826.1 | 18.4 | 30.4 GB | view |
| 16k | 708.4 | 17.9 | 31.7 GB | view |
| 32k | 644.9 | 17.2 | 34.2 GB | current |
| 64k | 550.8 | 16.1 | 39.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.8 | 1.00× |
| 2× | 34.1 | 1.81× |
| 4× | 72.8 | 3.87× |