← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
1,593
PP tok/s
72.8
TG tok/s
10289
TTFT (ms)
37.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,294 | 86.4 | 35.4 GB | view |
| 4k | 1,678 | 84.4 | 36.2 GB | view |
| 8k | 1,697 | 79.9 | 36.5 GB | view |
| 16k | 1,593 | 72.8 | 37.1 GB | current |
| 32k | 1,379 | 63.1 | 38.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 86.4 | 1.00× |
| 2× | 140.4 | 1.62× |
| 4× | 195.9 | 2.27× |