← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
16k
tokens
1,497
PP tok/s
72.8
TG tok/s
10944
TTFT (ms)
29.5
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
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,283 | 90.9 | 27.7 GB | view |
| 4k | 1,623 | 87.5 | 28.5 GB | view |
| 8k | 1,631 | 82.5 | 28.9 GB | view |
| 16k | 1,497 | 72.8 | 29.5 GB | current |
| 32k | 1,190 | 52.9 | 30.8 GB | view |
| 64k | 959.8 | 33.5 | 33.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 90.9 | 1.00× |
| 2× | 141.4 | 1.56× |
| 4× | 201.3 | 2.21× |