FAQ
Our new vGPU products are a variation of our popular root servers with high-quality hardware, but in this version they offer dedicated GPU resources in addition to guaranteed CPU performance. This makes these products particularly suitable for compute-intensive workloads such as AI inference, video encoding or data analysis.
Early Access gives you the opportunity to gain exclusive, early access to our new vGPU products. You can be one of the first to buy and test these products. We would also be delighted to hear your feedback and will send you a non-binding feedback form.
There may be various reasons for this. Please pay attention to the error message below the voucher field. Please also note that a code can only be redeemed once . Even if you do not complete the order but have already validated the code, it will no longer be valid if you enter it again. Therefore, please make sure to complete the order directly if possible. It is also not possible to redeem more than one code. If you have any problems, you can contact us using the following form.
Your individual code will be sent from 15.05. from approx. 11 am (CET). Please note that it may take some time before you find the corresponding e-mail in your mailbox. If the issue persists, feel free to contact us at: mail@netcup.de.
Yes, the number of vGPU servers in Early Access is limited. The principle of first come, first served applies. In addition, only one tariff per customer can be ordered during the Early Access phase to ensure fair distribution.
We have tested the new servers for the operation of several compact open source language models of different architectures. Below you will find a list of LLMs that are compatible with the listed tariffs.
RS 2000 vGPU 7 + RS 4000 vGPU 14
- llama3.2:1b
- llama3.2:3b
- llama3.1:8b
- mistral:7b
- gemma3:1b
- gemma3:4b
- phi3:3.8b
- deepseek-r1:1.5b
- deepseek-r1:7b
- deepseek-r1:8b
- qwen2.5:0.5b
- qwen2.5:1.5b
- qwen2.5:3b
- qwen2.5:7b
- qwen2.5-coder:0.5b
- qwen2.5-coder:1.5b
- qwen2.5-coder:3b
- qwen2.5-coder:7b
- qwen:0.5b
- qwen:1.8b
- qwen:4b
- qwen:7b
- gemma:2b
- gemma:7b
- qwen2:0.5b
- qwen2:1.5b
- qwen2:7b
- gemma2:2b
- llama2:7b
- tinyllama:1.1b
- starcoder2:3b
- starcoder2:7b
- dolphin3:8b
RS 4000 vGPU 14
- gemma3:12b
- deepseek-r1:14b
- phi4:14b
- qwen2.5:14b
- qwen2.5-coder:14b
- qwen:14b
- llama2:13b
- phi3:14b
- mistral-nemo:12b
- starcoder2:15b
