← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
64k
tokens
164.3
PP tok/s
30.2
TG tok/s
398958
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.5.0
macOS
macOS 26.5.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 318.9 | 58.1 | 19.3 GB | view |
| 4k | 346.2 | 55.6 | 20.0 GB | view |
| 8k | 338.2 | 52.8 | 20.5 GB | view |
| 16k | 300.5 | 47.3 | 20.6 GB | view |
| 32k | 254.4 | 40.7 | 20.7 GB | view |
| 64k | 164.3 | 30.2 | 21.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.1 | 1.00× |
| 2× | 127.6 | 2.20× |
| 4× | 242.4 | 4.17× |