← Back to community benchmarks
Qwen3.5-35B-A3B
Performance
8k
tokens
663.8
PP tok/s
47.3
TG tok/s
12340
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 656.7 | 54.4 | 20.1 GB | view |
| 4k | 685.1 | 50.0 | 20.2 GB | view |
| 8k | 663.8 | 47.3 | 20.4 GB | current |
| 16k | 609.9 | 37.5 | 20.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.4 | 1.00× |
| 2× | 84.9 | 1.56× |
| 4× | 115.2 | 2.12× |
| 8× | 144.9 | 2.66× |