← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
4k
tokens
452.4
PP tok/s
53.4
TG tok/s
9054
TTFT (ms)
17.2
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 356.4 | 56.3 | 16.4 GB | view |
| 4k | 452.4 | 53.4 | 17.2 GB | current |
| 8k | 447.4 | 48.0 | 17.6 GB | view |
| 16k | 432.9 | 37.7 | 18.2 GB | view |
| 32k | 397.0 | 27.1 | 19.5 GB | view |
| 64k | 331.2 | 17.2 | 22.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.3 | 1.00× |
| 2× | 77.2 | 1.37× |