← Back to community benchmarks
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-6bpw
Performance
16k
tokens
2,184
PP tok/s
73.1
TG tok/s
7503
TTFT (ms)
21.8
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
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,055 | 82.8 | 19.7 GB | view |
| 4k | 2,463 | 80.6 | 20.5 GB | view |
| 8k | 2,379 | 77.7 | 21.0 GB | view |
| 16k | 2,184 | 73.1 | 21.8 GB | current |
| 32k | 1,816 | 65.7 | 23.5 GB | view |
| 64k | 1,293 | 54.0 | 26.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.8 | 1.00× |
| 2× | 136.2 | 1.64× |
| 4× | 201.3 | 2.43× |
| 8× | 404.5 | 4.89× |