← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
8k
tokens
2,133
PP tok/s
85.0
TG tok/s
3842
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,467 | 97.1 | 19.9 GB | view |
| 4k | 2,087 | 92.0 | 20.7 GB | view |
| 8k | 2,133 | 85.0 | 21.0 GB | current |
| 16k | 2,013 | 79.4 | 21.7 GB | view |
| 32k | 1,744 | 68.3 | 23.0 GB | view |
| 64k | 1,332 | 52.6 | 25.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 97.1 | 1.00× |
| 2× | 155.2 | 1.60× |
| 4× | 221.4 | 2.28× |
| 8× | 324.9 | 3.35× |