← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
3,589
PP tok/s
90.7
TG tok/s
2282
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,947 | 100.8 | 35.4 GB | view |
| 4k | 3,942 | 97.3 | 36.2 GB | view |
| 8k | 3,589 | 90.7 | 36.5 GB | current |
| 16k | 3,208 | 91.9 | 37.1 GB | view |
| 32k | 2,842 | 88.8 | 38.5 GB | view |
| 64k | 2,035 | 76.2 | 41.2 GB | view |
| 128k | 1,204 | 56.5 | 46.5 GB | view |
| 195k | 842.3 | 44.0 | 52.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 100.8 | 1.00× |
| 2× | 152.8 | 1.52× |
| 4× | 217.6 | 2.16× |
| 8× | 430.8 | 4.27× |