4x RTX 3090 lab: Qwen3.6 on vLLM vs llama.cpp
| GPU(s) | 4x RTX 3090 Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 96 |
| CPU | |
| Motherboard | |
| RAM | |
| PSU | |
| Other | |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s |
|---|---|---|---|
| Qwen3.6 35B-A3B | IQ4_XS (1 GPU) | llama.cpp | 115-133 |
| Qwen3.6 35B-A3B | AWQ-INT4 (TP=2) | vLLM | 149 |
| Qwen3.6 35B-A3B | AWQ-INT4 + MTP-3 (TP=2) | vLLM | 225-231 |
Source: https://github.com/tfriedel/qwen3.6-rtx3090-lab
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: RunPod
Quick answers: Can 2x RTX 3090 run Qwen3.6 35B-A3B? · Can RTX 3090 run Qwen3.6 35B-A3B?