Search results

• NemoClaw

  NemoClaw

  NemoClaw for LangChain Deep Agents Code

  Run open-source Deep Agents Code, tuned for Nemotron 3 Ultra, to plan, edit and test code with enterprise governance.

  Blueprint
• tao-train-codetr

  Co-DETR (CoDINO) for object detection. A DETR-family detector with collaborative hybrid assignment — auxiliary one-to-many heads supervise the encoder during training, giving strong closed-set accuracy at high inference cost. Use when training, evaluating

  Skill
• General

  Developer Example

  Nsight Copilot - AI Code Assistant for CUDA Development

  Deploy an AI-powered coding assistant on DGX Spark that delivers expert CUDA-aware chat, real-time code completion, and retrieval-augmented generation grounded in authoritative GPU programming knowledge—powered by NVIDIA NIM microservices.

  Blueprint
• Intermediate30 MIN

  Set Up Claude Code with Local Inference

  A coding agent connected to a local Ollama model

  Playbook
• 30 MIN

  Vibe Coding in VS Code

  Use DGX Spark as a local or remote Vibe Coding assistant with Ollama and Continue

  Playbook
• Google

  DownloadableFree Endpoint

  diffusiongemma-26b-a4b-it

  Diffusion-based 26B parameter LLM enabling parallel token generation for real-time text apps

  Model
• Google

  DownloadableFree Endpoint

  gemma-4-31b-it

  Dense 31B model delivering frontier reasoning for coding, agentic workflows, and fine-tuning.

  Model
• OpenAI

  DownloadableFree Endpoint

  gpt-oss-20b

  Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math

  Model
• NVIDIA

  DownloadableFree Endpoint

  nemotron-3.5-lightning-30b-a3b

  Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks

  Model
• Microsoft

  Downloadable

  TRELLIS

  MSFT TRELLIS is a 3D AI model that generates high-quality 3D assets from text or image inputs.

  Model
• Z.ai

  Deprecation in 10dFree Endpoint

  glm-5-3

  753B-parameter text MoE with DeepSeek-style sparse attention, native FP8 weights, reasoning and tool calling.

  Model
• Stepfun-ai

  Free Endpoint

  Step 5 Preview

  Preview of StepFun's Step 5: ~600B-total / 27B-active multimodal MoE (text and image in, text out) with 1M context, reasoning and tool calling, served in NVFP4.

  Model
• Robotics

  Enterprise

  Synthetic Manipulation Motion Generation for Robotics

  Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.

  Blueprint
• NVIDIA

  DownloadableFree Endpoint

  cosmos3-nano

  Generates images, videos and action predictions from text, visual inputs and spatial controls, with mandatory input screening and visual SynthID watermarking.

  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
• Meta

  DownloadableFree Endpoint

  muse-glimmer-30b

  Muse Glimmer 30B is a multimodal reasoning model accepting text and images, with native tool-calling and separate reasoning output.

  Model
• Intermediate60 MIN

  Run Multi-Modal Inference with TensorRT

  GPU-accelerated text-to-image generation with diffusion models

  Playbook
• NVIDIA

  Free Endpoint

  magpie-tts-zeroshot

  Expressive and engaging text-to-speech, generated from a short audio sample.

  Model
• Qwen

  Downloadable

  qwen-image

  Qwen-Image is a text-to-image foundation model with advanced multilingual text rendering.

  Model
• Stability AI

  Downloadable

  stable-diffusion-3.5-large

  Stable Diffusion 3.5 is a popular text-to-image generation model

  Model
• tao-finetune-cosmos-embed

  Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "

  Skill