← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
32k
tokens
1,454
PP tok/s
90.2
TG tok/s
22539
TTFT (ms)
39.5
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,546 | 103.6 | 36.4 GB | view |
| 4k | 2,247 | 98.6 | 37.2 GB | view |
| 8k | 2,297 | 92.2 | 37.5 GB | view |
| 16k | 1,658 | 93.7 | 38.8 GB | view |
| 32k | 1,454 | 90.2 | 39.5 GB | current |
| 64k | 1,100 | 81.1 | 42.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 103.6 | 1.00× |
| 2× | 152.2 | 1.47× |
| 4× | 194.7 | 1.88× |
| 8× | 234.1 | 2.26× |