← Back to community benchmarks
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-5bpw
Performance
32k
tokens
1,772
PP tok/s
69.0
TG tok/s
18496
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.5.1
macOS
macOS 26.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,929 | 88.1 | 19.5 GB | view |
| 4k | 2,438 | 85.8 | 20.3 GB | view |
| 16k | 2,149 | 77.8 | 21.4 GB | view |
| 32k | 1,772 | 69.0 | 23.0 GB | current |
| 64k | 1,290 | 56.6 | 26.0 GB | view |
| 128k | 818.1 | 42.1 | 31.3 GB | view |
| 195k | 562.1 | 33.0 | 35.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 88.1 | 1.00× |
| 2× | 86.0 | 0.98× |
| 4× | 186.0 | 2.11× |
| 8× | 423.1 | 4.80× |