← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
743.6
PP tok/s
79.7
TG tok/s
5508
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.2.9
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 735.5 | 86.4 | 20.1 GB | view |
| 4k | 743.6 | 79.7 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 86.4 | 1.00× |
| 2× | 119.9 | 1.39× |
| 4× | 139.8 | 1.62× |
| 8× | 171.1 | 1.98× |