TokenSpeed is a speed-of-light LLM inference engine.

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

🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

The awesome collection of Nvidia NemoClaw presets, recipes, and playbooks for sandboxed OpenClaw operations.

On-device VAD / streaming STT / TTS / diarization in C++17 (ONNX + LiteRT) with a voice-agent pipeline. Linux, Windows, Android.

A GenAI-powered catalog enrichment system that transforms basic product images into comprehensive, rich catalog

Controllable reasoning demos for NVIDIA Nemotron 3 Super (120B/12B MoE) — chat UI, CLI, API server, tool calling, budget sweep, and adaptive routing

Interactive study + AI-powered interview practice tool for .NET 8 core AI Engineer interview topics.

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.

UDF + AI-Q + TTD DR + IaaC (AWS EKS and NIMs) + AG-UI + CopilotKit

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

Using the API use Nemotron without even needing any account in 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.

Talk. Ink. — Push-to-talk dictation for macOS, 100% on-device. Pick your model: Qwen3-ASR, NVIDIA Nemotron or Voxtral, all via Apple MLX.

Comprehensive benchmark of OpenRouter free-tier LLMs for practical applications. Evaluates models for coding, Thai language, and general use.

NemoClaw on DGX Spark: setup guide with local inference (Ollama + Atlas) and Nemotron 3 Super 120B benchmarks

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

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).

Hybrid AI Security Gateway — rule-based + LLM-assisted (Nemotron + Llama) prompt injection detection + MCP security (rules+policy+AI Assisted)

Lisa — Real-time Voice Assistant. Offline stack: Nemotron ASR, Gemma 4, XTTS, RAG, vision.