← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
32k
tokens
1,803
PP tok/s
59.6
TG tok/s
18178
TTFT (ms)
23.5
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.7
macOS
macOS 26.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,482 | 75.4 | 20.4 GB | view |
| 4k | 2,199 | 72.1 | 21.2 GB | view |
| 8k | 2,266 | 69.6 | 21.5 GB | view |
| 16k | 2,138 | 66.5 | 22.2 GB | view |
| 32k | 1,803 | 59.6 | 23.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.4 | 1.00× |
| 2× | 116.2 | 1.54× |