🚀 Nebul Adds Support for Alibaba’s 𝗤𝘄𝗲𝗻𝟯 Models 🚀
We’ve expanded our 𝗣𝗿𝗶𝘃𝗮𝘁𝗲 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗔𝗣𝗜 and 𝗣𝗿𝗶𝘃𝗮𝘁𝗲𝗚𝗣𝗧 offerings with the addition of Alibaba’s latest large language models, the Qwen3 family. These models represent a significant step forward from their previous QwQ and Qwen2.5 iterations, offering notable advancements in several key areas.
Qwen3 features a flexible architecture that allows for dynamic switching between a deliberate “𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝗺𝗼𝗱𝗲” for complex reasoning and a fast “non-thinking mode” for efficient general chat. The models also provide extensive multilingual support, covering over 𝟭𝟬𝟬 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲𝘀 𝗮𝗻𝗱 𝗱𝗶𝗮𝗹𝗲𝗰𝘁𝘀, and demonstrate improved capabilities for integrating with external tools for 𝗮𝗴𝗲𝗻𝘁-𝗯𝗮𝘀𝗲𝗱 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀.
Our team has been evaluating the performance of the Qwen3 models, particularly the 32B variant, across various GPU configurations over the past few days. Initial results indicate strong performance in both throughput and the quality of generated output.
Qwen3 is now available on our platform, providing users with access to advanced AI capabilities within a 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 and 𝘀𝗲𝗰𝘂𝗿𝗲 environment.
For more information or to schedule a demonstration feel free to get in touch with us!
Jumpstart with an easy to use product that runs NVIDIA-optimized Open-Source models with integrated privacy, security and guardrails.
Private AI Models is a secure inferencing service run on its own private Neocloud, ensuring compliance and data protection.
A new generation of cloud that offers specialized high-performance compute and storage solutions, particularly focused on serving AI-workloads.
The apex supercomputing solution from Europe: A large-scale GPU clusters that is reaching optimal performance at scale.