← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
1,494
PP tok/s
71.4
TG tok/s
10968
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.2
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,624 | 80.9 | 35.5 GB | view |
| 4k | 1,656 | 79.0 | 36.2 GB | view |
| 8k | 1,653 | 76.4 | 36.3 GB | view |
| 16k | 1,494 | 71.4 | 36.5 GB | current |
| 32k | 1,248 | 68.2 | 36.8 GB | view |
| 64k | 935.9 | 57.4 | 37.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.9 | 1.00× |
| 2× | 131.2 | 1.62× |
| 4× | 196.1 | 2.42× |
| 8× | 275.4 | 3.40× |