← Back to community benchmarks
Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16
Performance
32k
tokens
63.0
PP tok/s
10.2
TG tok/s
520124
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 65.3 | 12.5 | 15.8 GB | view |
| 4k | 62.5 | 12.3 | 17.3 GB | view |
| 8k | 63.8 | 11.5 | 18.3 GB | view |
| 16k | 64.1 | 11.8 | 19.8 GB | view |
| 32k | 63.0 | 10.2 | 22.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.5 | 1.00× |
| 2× | 15.7 | 1.26× |
| 4× | 17.6 | 1.41× |
| 8× | 14.5 | 1.16× |