← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
128k
tokens
267.6
PP tok/s
19.4
TG tok/s
489764
TTFT (ms)
46.5
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
96 GB
GPU Cores
30
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 589.4 | 40.7 | 35.4 GB | view |
| 4k | 645.3 | 41.6 | 36.2 GB | view |
| 8k | 712.4 | 41.7 | 36.5 GB | view |
| 16k | 682.6 | 38.4 | 37.1 GB | view |
| 32k | 570.1 | 33.7 | 38.5 GB | view |
| 64k | 435.5 | 26.1 | 41.2 GB | view |
| 128k | 267.6 | 19.4 | 46.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.7 | 1.00× |
| 2× | 62.3 | 1.53× |