← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
4k
tokens
684.8
PP tok/s
51.7
TG tok/s
5982
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 640.1 | 54.6 | 20.1 GB | view |
| 4k | 684.8 | 51.7 | 20.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.6 | 1.00× |
| 2× | 83.0 | 1.52× |
| 4× | 113.9 | 2.09× |
| 8× | 143.8 | 2.63× |