← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
2,399
PP tok/s
89.3
TG tok/s
3416
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,084 | 96.2 | 19.3 GB | view |
| 4k | 2,479 | 93.4 | 20.1 GB | view |
| 8k | 2,399 | 89.3 | 20.5 GB | current |
| 16k | 2,187 | 83.2 | 21.4 GB | view |
| 32k | 1,830 | 73.5 | 23.1 GB | view |
| 64k | 1,319 | 59.3 | 25.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.2 | 1.00× |
| 2× | 159.6 | 1.66× |
| 4× | 218.8 | 2.27× |
| 8× | 430.7 | 4.48× |