← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
8k
tokens
1,670
PP tok/s
82.9
TG tok/s
4906
TTFT (ms)
28.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,318 | 90.6 | 27.7 GB | view |
| 4k | 1,671 | 87.4 | 28.5 GB | view |
| 8k | 1,670 | 82.9 | 28.9 GB | current |
| 16k | 1,511 | 77.1 | 29.5 GB | view |
| 32k | 1,194 | 53.3 | 30.8 GB | view |
| 64k | 951.7 | 34.3 | 33.5 GB | view |
| 128k | 529.5 | 19.3 | 38.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 90.6 | 1.00× |
| 2× | 142.1 | 1.57× |
| 4× | 176.8 | 1.95× |