← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
2,060
PP tok/s
68.2
TG tok/s
1988
TTFT (ms)
66.4
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,424 | 71.8 | 65.6 GB | view |
| 4k | 2,060 | 68.2 | 66.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.8 | 1.00× |
| 2× | 68.3 | 0.95× |
| 4× | 120.9 | 1.68× |