Latest news with #Alibabahas

Hans India

Alibaba Launches Qwen3 AI Models, Taking Bold Aim at ChatGPT and Gemini

Alibabahas made another major move in the AI race by launching a new series of largelanguage models called Qwen3, designed to compete directly with OpenAI'sChatGPT and Google's Gemini. The announcement came on Monday through a detailedpost on X, where the Chinese tech giant outlined the capabilities of its latestAI models. 'We areexcited to announce the release of Qwen3, the latest addition to the Qwenfamily of large language models,' Alibaba stated in an official blog post. Theflagship model, Qwen3-235B-A22B, reportedly delivers impressive resultsin areas such as mathematics, coding, and general reasoning. According toAlibaba, its performance rivals or even surpasses top-tier models likeDeepSeek-R1, o1, o3-mini, Grok-3, and Gemini-2.5-Pro. Introducing Qwen3! We release and open-weight Qwen3, our latest large language models, including 2 MoE models and 6 dense models, ranging from 0.6B to 235B. Our flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general… — Qwen (@Alibaba_Qwen) April 28, 2025 Onestandout feature of Qwen3 is its multilingual support. The models areequipped to understand and generate content in 119 languages, includingIndian languages like Hindi, Gujarati, Marathi, Punjabi, Bengali, Sindhi, andeven region-specific dialects such as Chhattisgarhi, Maithili, and Awadhi. The Qwen3family comprises eight models, with sizes ranging from 0.6 billion to235 billion parameters. This includes both dense models and Mixtureof Experts (MoE) architectures, providing options that cater to differentperformance needs and computational constraints. Alibabahighlights the power of its top-tier models:'The small MoE model, Qwen3-30B-A3B, outcompetes QwQ-32B with 10 times ofactivated parameters, and even a tiny model like Qwen3-4B can rival theperformance of Qwen2.5-72B-Instruct,' the company noted. We also evaluated the preliminary performance of Qwen3-235B-A22B on the open-source coding agent Openhands. It achieved 34.4% on Swebench-verified, achieving competitive results with fewer parameters! Thanks to @allhands_ai for providing an easy-to-use agent. Both open models and… — Qwen (@Alibaba_Qwen) April 29, 2025 Topromote open research and development, Alibaba is releasing open-weightversions of both large and compact models. These include the 235B and 30Bparameter MoE models, along with six dense models under the Apache 2.0 license:Qwen3-32B, 14B, 8B, 4B, 1.7B, and 0.6B. Themodels are readily available on platforms like Hugging Face, ModelScope,and Kaggle, with both pre-trained and post-trained variants. Fordeployment, Alibaba recommends tools like SGLang and vLLM, whilelocal setups can use Ollama, LMStudio, MLX, KTransformers. Qwen3 exhibits scalable and smooth performance improvements that are directly correlated with the computational reasoning budget allocated. This design enables users to configure task-specific budgets with greater ease, achieving a more optimal balance between cost efficiency and… — Qwen (@Alibaba_Qwen) April 28, 2025 One ofthe most innovative aspects of Qwen3 is its scalable performancearchitecture. Users can customise the AI's output quality based onavailable compute resources, striking a balance between speed, cost, and depthof understanding. This is particularly useful for coding and complex,multi-step reasoning tasks. We also evaluated the preliminary performance of Qwen3-235B-A22B on the open-source coding agent Openhands. It achieved 34.4% on Swebench-verified, achieving competitive results with fewer parameters! Thanks to @allhands_ai for providing an easy-to-use agent. Both open models and… — Qwen (@Alibaba_Qwen) April 29, 2025