← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
2,182
PP tok/s
87.4
TG tok/s
3755
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,497 | 95.9 | 19.3 GB | view |
| 4k | 2,159 | 95.9 | 20.0 GB | view |
| 8k | 2,182 | 87.4 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.9 | 1.00× |
| 2× | 142.3 | 1.48× |
| 4× | 190.8 | 1.99× |
| 8× | 239.9 | 2.50× |