← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
2,072
PP tok/s
82.9
TG tok/s
1977
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,491 | 85.3 | 35.4 GB | view |
| 4k | 2,072 | 82.9 | 36.2 GB | current |
| 32k | 1,735 | 62.5 | 38.5 GB | view |
| 64k | 1,323 | 44.9 | 41.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.3 | 1.00× |
| 2× | 142.2 | 1.67× |
| 4× | 284.0 | 3.33× |