← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
32k
tokens
3,448
PP tok/s
93.2
TG tok/s
9504
TTFT (ms)
23.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2rc1
macOS
macOS 26.5.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,868 | 111.7 | 20.4 GB | view |
| 4k | 3,838 | 105.6 | 21.2 GB | view |
| 8k | 4,270 | 103.7 | 21.5 GB | view |
| 16k | 4,031 | 100.7 | 22.4 GB | view |
| 32k | 3,448 | 93.2 | 23.9 GB | current |
| 64k | 2,450 | 79.1 | 26.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 111.7 | 1.00× |
| 2× | 162.4 | 1.45× |
| 4× | 258.2 | 2.31× |