← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
3,945
PP tok/s
99.2
TG tok/s
4154
TTFT (ms)
29.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.3
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,096 | 102.1 | 27.4 GB | view |
| 4k | 4,004 | 104.3 | 28.3 GB | view |
| 8k | 4,431 | 99.5 | 28.8 GB | view |
| 16k | 3,945 | 99.2 | 29.5 GB | current |
| 32k | 3,345 | 91.3 | 31.0 GB | view |
| 64k | 2,396 | 77.6 | 33.9 GB | view |
| 128k | 1,505 | 62.3 | 39.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 102.1 | 1.00× |
| 2× | 185.5 | 1.82× |
| 4× | 270.2 | 2.65× |