← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
32k
tokens
1,098
PP tok/s
66.9
TG tok/s
29836
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,099 | 104.4 | 18.3 GB | view |
| 4k | 1,368 | 100.7 | 19.0 GB | view |
| 8k | 1,357 | 92.3 | 19.4 GB | view |
| 16k | 1,272 | 81.9 | 20.0 GB | view |
| 32k | 1,098 | 66.9 | 21.3 GB | current |
| 64k | 838.6 | 43.5 | 24.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.4 | 1.00× |
| 2× | 169.9 | 1.63× |
| 4× | 237.9 | 2.28× |