← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
4,706
PP tok/s
122.7
TG tok/s
1741
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.3
macOS
macOS 26.5.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,808 | 130.1 | 19.4 GB | view |
| 4k | 4,835 | 131.3 | 20.2 GB | view |
| 8k | 4,706 | 122.7 | 20.7 GB | current |
| 16k | 4,301 | 116.2 | 21.4 GB | view |
| 32k | 3,536 | 108.7 | 22.9 GB | view |
| 64k | 2,549 | 92.1 | 25.8 GB | view |
| 128k | 1,595 | 71.6 | 31.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 130.1 | 1.00× |
| 2× | 238.3 | 1.83× |
| 4× | 351.0 | 2.70× |