← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
128k
tokens
1,198
PP tok/s
40.6
TG tok/s
109432
TTFT (ms)
26.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
64 GB
GPU Cores
40
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 | 1,150 | 102.8 | 19.0 GB | view |
| 4k | 1,431 | 96.7 | 19.8 GB | view |
| 8k | 1,449 | 90.5 | 20.1 GB | view |
| 32k | 2,676 | 90.0 | 21.9 GB | view |
| 64k | 2,035 | 81.1 | 23.8 GB | view |
| 128k | 1,198 | 40.6 | 26.4 GB | current |
| 195k | 846.0 | 43.9 | 29.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 102.8 | 1.00× |
| 2× | 136.1 | 1.32× |
| 4× | 176.1 | 1.71× |
| 8× | 198.3 | 1.93× |