Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
-
Updated
Jun 4, 2026 - Jupyter Notebook
#
nemotron
Here are 83 public repositories matching this topic...
🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀
gemini openai glm gpt termux minimax grok codex ai-agents claude kimi ai-assistant llm generative-ai qwen deepseek agentic-ai nemotron ai-coding-agent
-
Updated
May 26, 2026 - TypeScript
The awesome collection of Nvidia NemoClaw presets, recipes, and playbooks for sandboxed OpenClaw operations.
-
Updated
Mar 17, 2026
On-device VAD / streaming STT / TTS / diarization in C++17 (ONNX + LiteRT) with a voice-agent pipeline. Linux, Windows, Android.
android text-to-speech speech-recognition cpp17 speech-to-text speaker-diarization voice-activity-detection speech-enhancement on-device litert kokoro tflite parakeet edge-ai onnxruntime voice-agent streaming-asr silero pyannote nemotron
-
Updated
Jun 15, 2026 - C++
Interactive study + AI-powered interview practice tool for .NET 8 core AI Engineer interview topics.
azure terraform architecture sonarqube nvidia iac azure-functions structurzr nemotron claude-code nemotron-ai claude-agents claude-ai-skills
-
Updated
May 12, 2026 - JavaScript
29 controlled experiments on Nemotron 3 Ultra: what prompting can and cannot do to a frontier model. Voice 4/8 to 7/8, hidden bugs 1/5 to 5/5 — blind dual-judge graded, no fine-tuning.
-
Updated
Jun 11, 2026 - Python
An AI-to-AI robot podcast hosted by Reachy Mini robots — live LLM+TTS generated shows, 3D twins, a radio station, and a physical-robot companion
-
Updated
Jun 15, 2026 - JavaScript
Talk. Ink. — Push-to-talk dictation for macOS, 100% on-device. Pick your model: Qwen3-ASR, NVIDIA Nemotron or Voxtral, all via Apple MLX.
macos swift open-source privacy speech-recognition speech-to-text dictation asr mlx swiftui on-device-ai apple-silicon qwen nemotron voxtral whisper-alternative
-
Updated
Jun 16, 2026 - Swift
UDF + AI-Q + TTD DR + IaaC (AWS EKS and NIMs) + AG-UI + CopilotKit
docker kubernetes aws nim terraform nextjs nvidia rag eks langgraph copilotkit nemotron deep-research ag-ui
-
Updated
Dec 23, 2025 - Python
Hermes skill for subtitle-first video reporting with configurable ASR backends, visual evidence, and Markdown/HTML/PDF output
-
Updated
Jun 12, 2026 - Python
AI-powered business analytics agent built on 6 NVIDIA models: Ultra 253B, Nano 8B, Vision 12B VL, NV-EmbedQA-E5-v5 + self-hosted RTX 4090. 4-tier intent routing, PhD-level statistical analysis. Live at lubot.ai
-
Updated
Mar 3, 2026 - Python
Using the API use Nemotron without even needing any account in python
python api nvidia openai api-wrapper language-model claude chatgpt chatgpt-free nemotron nemotron-ai
-
Updated
Jul 19, 2025 - Python
Agentic AI Career Coach powered by NVIDIA Nemotron (NIM). FastAPI + minimal web UI that parses resumes, analyzes strengths/skill gaps, and fetches live jobs via MCP.
python nim hackathon mcp nvidia resume-parser job-search uvicorn fastapi career-coach agentic-ai nemotron
-
Updated
Oct 20, 2025 - Python
Comprehensive benchmark of OpenRouter free-tier LLMs for practical applications. Evaluates models for coding, Thai language, and general use.
thai-language thai-nlp gemma model-evaluation openrouter ai-gateway nemotron llm-comparison llm-benchmark free-ai-models openclaw step-flash trinity-mini chatbot-benchmark free-tier-llm
-
Updated
Feb 24, 2026
NVFP4 LoRA fine-tuning and serving on a single NVIDIA DGX Spark (GB10, 128 GB UMA). Fused Triton dequant; multi-family (Nemotron-3, Mistral-Small-4, Qwen3.x).
agent ai nvidia moe hermes lora nvidia-gpu peft mixture-of-experts quantisation vllm qlora local-ai fp4 agentic-ai nemotron nvidia-blackwell nvfp4 dgx-spark openclaw
-
Updated
Jun 14, 2026 - Python
An AI agent that runs as a profitable, self-funding business: earns via Stripe, fulfils with NVIDIA Nemotron, pays its own vendor bills, never works at a loss.
-
Updated
Jun 18, 2026 - Python
Hybrid Mamba-2 + Transformer 2.94B LLM (Nemotron-H style) — Korean 3B model pretrained from scratch on 7× NVIDIA B200 GPUs with SFT + DPO alignment
-
Updated
Mar 26, 2026 - Python
Improve this page
Add a description, image, and links to the nemotron topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nemotron topic, visit your repo's landing page and select "manage topics."