← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
16k
tokens
653.9
PP tok/s
47.1
TG tok/s
25055
TTFT (ms)
37.0
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 729.8 | 56.6 | 36.2 GB | view |
| 4k | 735.2 | 54.1 | 36.3 GB | view |
| 8k | 709.7 | 51.7 | 36.5 GB | view |
| 16k | 653.9 | 47.1 | 37.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.6 | 1.00× |
| 2× | 86.4 | 1.53× |
| 4× | 104.5 | 1.85× |
| 8× | 129.0 | 2.28× |