← Back to community benchmarks
Qwen3.6-35B-A3B-OptiQ
Performance
64k
tokens
2,498
PP tok/s
80.8
TG tok/s
26235
TTFT (ms)
28.3
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
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,772 | 111.7 | 21.8 GB | view |
| 4k | 4,791 | 108.9 | 22.7 GB | view |
| 8k | 4,630 | 105.6 | 23.1 GB | view |
| 16k | 4,254 | 101.8 | 23.9 GB | view |
| 32k | 3,579 | 95.0 | 25.4 GB | view |
| 64k | 2,498 | 80.8 | 28.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 111.7 | 1.00× |
| 2× | 196.9 | 1.76× |
| 4× | 300.2 | 2.69× |