← Back to community benchmarks
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-6bpw
Performance
32k
tokens
1,821
PP tok/s
65.8
TG tok/s
17996
TTFT (ms)
23.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,057 | 82.8 | 19.7 GB | view |
| 4k | 2,460 | 80.9 | 20.5 GB | view |
| 8k | 2,384 | 78.0 | 21.0 GB | view |
| 16k | 2,183 | 73.2 | 21.7 GB | view |
| 32k | 1,821 | 65.8 | 23.6 GB | current |
| 64k | 1,296 | 53.9 | 26.2 GB | view |
| 128k | 775.7 | 37.7 | 32.6 GB | view |
| 195k | 520.2 | 30.3 | 39.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.8 | 1.00× |
| 2× | 135.9 | 1.64× |
| 4× | 198.1 | 2.39× |
| 8× | 373.1 | 4.51× |