← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
2,131
PP tok/s
93.0
TG tok/s
3844
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
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 | 1,491 | 103.6 | 19.3 GB | view |
| 4k | 2,098 | 100.6 | 20.0 GB | view |
| 8k | 2,131 | 93.0 | 20.4 GB | current |
| 16k | 2,017 | 83.5 | 21.0 GB | view |
| 32k | 1,745 | 70.4 | 22.4 GB | view |
| 64k | 1,315 | 48.9 | 25.0 GB | view |
| 128k | 838.1 | 26.7 | 30.4 GB | view |
| 195k | 606.9 | 14.5 | 36.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 103.6 | 1.00× |
| 2× | 174.5 | 1.68× |
| 4× | 261.9 | 2.53× |
| 8× | 378.2 | 3.65× |