NVIDIA NIM Microservice Now Available to Streamline Agent Workflows on RTX AI PCs and Workstations
NVIDIA NIM microservices make AI applications on PCs and workstations easier to use, accelerating AI development and popularization.
Core content:
1. NVIDIA NIM microservices and AI Blueprints help AI development, suitable for RTX AI PCs and workstations
2. Provide pre-packaged AI models optimized for NVIDIA RTX platforms, covering a variety of application scenarios
3. Support AI ecosystem tools and frameworks to simplify AI model deployment and application development processes
Generative AI brings new capabilities to PCs and workstations, including gaming assistants, enhanced content creation and productivity tools, and more.
Available now, NVIDIA NIM microservices and upcoming AI Blueprints accelerate AI development and usability. Launched at CES in January, NVIDIA NIM provides pre-packaged state-of-the-art AI models optimized for NVIDIA RTX platforms, including NVIDIA GeForce RTX 50 series and the new NVIDIA Blackwell RTX PRO GPUs. Microservices are easy to download and run. Microservices cover top PC development modalities and are compatible with top ecosystem applications and tools.
At a critical moment in computing, where breakthrough AI models and a global developer community are driving an explosion of AI-enabled tools and workflows, NIM microservices and AI Blueprint are helping to bring critical innovations to the PC.
NIM helps you get started right away
Despite the incredible pace of innovation in AI, the PC developer community still has a hard time getting started with the technology.
Bringing AI models from research to PCs requires model variant management, adaptive management of input and output data, and quantization to optimize resource usage. In addition, models must be converted to work with optimized inference backend software and connected to new AI application programming interfaces (APIs). This requires a huge effort and may slow down the adoption of AI.
NVIDIA NIM microservices help solve this problem by providing prepackaged, optimized, easy-to-download AI models that connect to industry-standard APIs. They are optimized for performance on RTX AI PCs and workstations and include top AI models from the community as well as models developed by NVIDIA.
NIM microservices support various AI applications, including large language models (LLMs), visual language models, image generation, speech processing, search based on retrieval augmented generation (RAG), PDF extraction, and computer vision. Ten NIM microservices for RTX are provided to support various applications, including language and image generation, computer vision, speech AI, etc.
Visit https://www.nvidia.cn/ai/ to get started with the following NIMs:
Language and Reasoning: Deepseek-R1-distill-llama-8B, Mistral-nemo-12B-instruct and Llama3.1-8B-instruct
Image generation: Flux.dev
Audio: Riva Parakeet-ctc-0.6B-asr and Maxine Studio Voice
RAG: Llama-3.2-NV-EmbedQA-1B-v2
Computer Vision and Understanding: NV-CLIP, PaddleOCR, and Yolo-X-v1
NIM microservices are also available through top AI ecosystem tools and frameworks.
For AI enthusiasts, AnythingLLM and ChatRTX now support NIM, making it easy to chat with LLM and AI agents through a simple, user-friendly interface. With these tools, users can create personalized AI assistants and integrate their own documents and data to help automate tasks and improve productivity.
For developers who want to build, test, and integrate AI into their applications, FlowiseAI and Langflow now support NIM and provide low-code and no-code solutions with visual interfaces to design AI workflows with minimal programming expertise. Support for ComfyUI is coming soon. With these tools, developers can easily create complex AI applications such as chatbots, image generators, and data analysis systems.
Additionally, Microsoft VS Code AI Toolkit, CrewAI, and Langchain now support NIM and provide advanced capabilities for integrating microservices into application code, helping to ensure seamless integration and optimization.
NVIDIA AI Blueprint,
Provides pre-built workflows
NVIDIA AI Blueprint gives AI developers a head start in building generative AI workflows with NVIDIA NIM microservices.
Blueprints are ready-to-use, extensible reference samples that package all the necessary elements (source code, sample data, documentation, and demo applications) to create and customize advanced AI workflows that run locally. Developers can modify and extend AI Blueprints to adjust their behavior, use different models, or implement entirely new features.
PDF to Podcast AI Blueprint converts documents into audio content so that users can learn anytime, anywhere. By extracting text, images, and tables from PDFs, the workflow uses AI to generate informative podcasts. To explore topics more deeply, users can engage in interactive discussions with AI-powered podcast hosts.
With Windows Subsystem for Linux,
Running NVIDIA NIM and AI Blueprint on RTX
One of the key technologies that enables NIM microservices to run on PC is Windows Subsystem for Linux (WSL).
Microsoft and NVIDIA have collaborated to bring CUDA and RTX acceleration to WSL, making it possible to run optimized, containerized microservices on Windows. This enables the same NIM microservices to run anywhere, anytime, from PCs and workstations to data centers and the cloud.
Visit www.nvidia.com/ai/ to get started with NVIDIA NIM and AI Blueprint on your RTX AI PC .
Build, Create, Innovate
NVIDIA NIM microservices and AI Blueprint for RTX are available now at www.nvidia.com/ai/ , providing developers and AI enthusiasts with powerful, ready-to-use tools for building AI applications.
