← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
723.1
PP tok/s
74.7
TG tok/s
11329
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.2.9
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 744.5 | 85.6 | 20.1 GB | view |
| 4k | 750.4 | 80.4 | 20.2 GB | view |
| 8k | 723.1 | 74.7 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.6 | 1.00× |
| 2× | 121.3 | 1.42× |
| 4× | 142.5 | 1.66× |