← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
3,457
PP tok/s
64.7
TG tok/s
2370
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,786 | 67.0 | 65.6 GB | view |
| 4k | 3,202 | 65.3 | 66.4 GB | view |
| 8k | 3,457 | 64.7 | 66.7 GB | current |
| 16k | 3,501 | 65.3 | 67.6 GB | view |
| 32k | 3,105 | 61.2 | 69.1 GB | view |
| 64k | 2,300 | 54.2 | 72.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.0 | 1.00× |
| 2× | 64.5 | 0.96× |
| 4× | 110.3 | 1.65× |
| 8× | 130.8 | 1.95× |