← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
128k
tokens
853.9
PP tok/s
30.7
TG tok/s
153491
TTFT (ms)
76.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.5
macOS
macOS 26.3
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,458 | 70.4 | 65.6 GB | view |
| 4k | 2,115 | 66.8 | 66.4 GB | view |
| 8k | 2,148 | 66.5 | 66.7 GB | view |
| 16k | 2,037 | 61.3 | 67.4 GB | view |
| 32k | 1,758 | 53.4 | 68.7 GB | view |
| 64k | 1,338 | 43.4 | 71.3 GB | view |
| 128k | 853.9 | 30.7 | 76.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.4 | 1.00× |
| 2× | 67.0 | 0.95× |
| 4× | 119.2 | 1.69× |
| 8× | 70.4 | 1.00× |