← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
1,489
PP tok/s
45.4
TG tok/s
2751
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 27.0
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 922.1 | 48.3 | 35.4 GB | view |
| 4k | 1,489 | 45.4 | 36.2 GB | current |
| 8k | 1,478 | 46.2 | 36.7 GB | view |
| 16k | 1,399 | 45.4 | 37.7 GB | view |
| 32k | 1,246 | 41.0 | 38.9 GB | view |
| 64k | 918.8 | 32.9 | 42.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.3 | 1.00× |
| 2× | 77.9 | 1.61× |
| 4× | 110.4 | 2.29× |