← Back to community benchmarks
Qwen3.6-27B-Uncensored-Heretic-v2
Performance
1k
tokens
715.9
PP tok/s
24.5
TG tok/s
1430
TTFT (ms)
22.1
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 715.9 | 24.5 | 22.1 GB | current |
| 4k | 852.6 | 23.7 | 23.5 GB | view |
| 8k | 775.5 | 24.1 | 24.2 GB | view |
| 16k | 700.2 | 23.4 | 25.4 GB | view |
| 32k | 641.6 | 22.0 | 27.9 GB | view |
| 64k | 557.7 | 19.4 | 32.9 GB | view |
| 128k | 421.9 | 16.5 | 40.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.5 | 1.00× |
| 2× | 36.9 | 1.51× |
| 4× | 92.9 | 3.79× |