Skip to main content
NVIDIA
65 results for

Search results

  • 20 MIN

    Live VLM WebUI

    Real-time Vision Language Model interaction with webcam streaming
    Playbook

  • How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-agent), and health checks.
    Skill

  • Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and false negatives", or identify failure cases from a predict
    Skill

  • Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
    Skill
  • 1 HR

    Vision-Language Model Fine-tuning

    Fine-tune Vision-Language Models for image and video understanding tasks using Qwen2.5-VL and InternVL3
    Playbook
  • Intermediate2 HOURS

    Fine-Tune Vision Language Models

    Image and video understanding adapted to your own specialized tasks
    Playbook
  • Intermediate30 MIN

    Stream Real-Time Video to a Vision Language Model

    A webcam-based testbed for comparing VLMs across backends
    Playbook
  • Google
    Free Endpoint

    paligemma

    Vision language model adept at comprehending text and visual inputs to produce informative responses
    Model
  • 1 HR

    TRT LLM for Inference

    Install and use TensorRT-LLM on DGX Spark
    Playbook
  • NVIDIA
    DownloadableFree Endpoint

    nemotron-3-nano-omni-30b-a3b-reasoning

    Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
    Model

  • Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
    Skill
  • Z.ai
    Deprecation in 5dFree Endpoint

    glm-5-3

    753B-parameter text MoE with DeepSeek-style sparse attention, native FP8 weights, reasoning and tool calling.
    Model
  • Z.ai
    Free Endpoint

    glm-5-3-flash

    Multimodal 320B-total / 18B-active MoE with hybrid KDA and sparse MLA attention, native FP8 weights, reasoning and tool calling.
    Model

  • Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.
    Skill

  • Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.
    Skill
  • Intermediate30 MIN

    Serve LLMs with vLLM on One Device

    A locally accessible model API from one DGX Spark or Station
    Playbook
  • Intermediate30 MIN

    Serve LLMs with vLLM Across DGX Sparks

    Guided and configurable model serving across DGX Spark clusters
    Playbook
  • Intermediate30 MIN

    Deploy NVIDIA NIM for LLM Inference

    Prebuilt, GPU-optimized model containers with a ready-to-use HTTP endpoint
    Playbook
  • Intermediate30 MIN

    Run Hermes Agent with a Local LLM

    Chat from the terminal against local vLLM with the self-improving Nous Research agent (Telegram optional)
    Playbook
  • Intermediate30 MIN

    Run NemoClaw with a Local LLM

    Build a local AI assistant in an OpenShell sandbox with vLLM inference and optional Telegram
    Playbook
  • 30 MIN

    LM Studio on DGX Spark

    Deploy LM Studio and serve LLMs on a Spark device; use LM Link to access models remotely.
    Playbook
  • Intermediate30 MIN

    Run OpenClaw with a Local LLM

    Install a local-first AI agent and connect it to a private OpenAI-compatible model endpoint
    Playbook
  • Intermediate30 MIN

    Serve LLMs with LM Studio

    Local models reachable from your own machine's tools over an encrypted link
    Playbook
  • NVIDIA
    Downloadable

    llama-nemotron-embed-vl-1b-v2

    Multimodal question-answer retrieval representing user queries as text and documents as images.
    Model
Items per page
of 3 pages