← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
1,751
PP tok/s
99.6
TG tok/s
2339
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,703 | 104.3 | 20.1 GB | view |
| 4k | 1,751 | 99.6 | 20.2 GB | current |
| 8k | 1,598 | 93.3 | 20.4 GB | view |
| 16k | 1,319 | 81.7 | 20.8 GB | view |
| 32k | 757.7 | 49.2 | 21.6 GB | view |
| 64k | 486.0 | 45.7 | 23.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.3 | 1.00× |
| 2× | 158.9 | 1.52× |
| 4× | 203.5 | 1.95× |
| 8× | 252.2 | 2.42× |