Ext Ops Panel
Open dashboard

ModelOpt

Skills for Model Optimizer development, quantization, deployment, and evaluation.

Plugin bundle · by NVIDIA Corporation

About

ModelOpt is a plugin bundle for AI coding tools published by NVIDIA Corporation. Marketplaces we read that list it: 1 (Community GitHub marketplaces). The last change we recorded was on 2026-11-15. As of our marketplace pass on 2026-11-15.

What it asks for

  • Installs as a plugin bundle

None of the marketplaces we read publishes its tools or the settings it asks for.

What it declares, asks for and runs, in full

Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.

Works with

  • Claude Code

From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.

Connect

Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.

As a Claude Code plugin

Built from what Community GitHub marketplaces declares.

Claude CodeInside a Claude Code session
/plugin marketplace add nvidia/model-optimizer
/plugin install modelopt@modelopt

Where it is published

MarketplaceStatusVersionFiguresVerifiedFirst seen
Community marketplace nvidia/model-optimizer (Open the source on GitHub) Listed 0.1.0 Forks (GitHub): 808
Stars (GitHub): 5 608
Not marked

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

Listed in one community marketplace
MarketplaceRepositoryStars (GitHub)
modelopt nvidia/model-optimizer 5 608

Which marketplaces we read and how we check them

How its figures have moved

Forks (GitHub)
+20 since 02.11
788-808 · 7 readings
  1. 2026-11-02788
  2. 2026-11-03792
  3. 2026-11-04800
  4. 2026-11-07803
  5. 2026-11-09805
  6. 2026-11-14807
  7. 2026-11-15808
Stars (GitHub)
+115 since 02.11
5.5k-5.6k · 10 readings
  1. 2026-11-025.5k
  2. 2026-11-035.5k
  3. 2026-11-045.5k
  4. 2026-11-065.5k
  5. 2026-11-075.6k
  6. 2026-11-095.6k
  7. 2026-11-105.6k
  8. 2026-11-125.6k
  9. 2026-11-145.6k
  10. 2026-11-155.6k

Each dot is a day we read a different number; flat stretches are days the number did not move. Figures of different marketplaces are never added up.

What the bundle contains

As published on Community GitHub marketplaces.

MCP servers: 1

  • modelopt

Skills: 31

  • accessing-mlflow
  • benchmark-model-kernels
  • common
  • compare-results
  • day0-release
  • debug
  • deployment
  • evaluation
  • launching-evals
  • modelopt-accessing-mlflow
  • modelopt-benchmark-model-kernels
  • modelopt-compare-results
Show the remaining 19
  • modelopt-day0-release
  • modelopt-debug
  • modelopt-deployment
  • modelopt-evaluation
  • modelopt-launching-evals
  • modelopt-monitor
  • modelopt-ptq
  • modelopt-qad
  • modelopt-quant-recipe-search
  • modelopt-release-cherry-pick
  • modelopt-run-agentx
  • modelopt-speculative-decoding
  • monitor
  • ptq
  • qad
  • quant-recipe-search
  • release-cherry-pick
  • run-agentx
  • speculative-decoding

Agents: 6

  • modelopt-model-distiller
  • modelopt-model-downloader
  • modelopt-model-evaluator
  • modelopt-model-performance-benchmarker
  • modelopt-model-quantize-recipe-searcher
  • modelopt-model-quantizer

What changed

  1. Community GitHub marketplaces: repository or package changed
  2. Community GitHub marketplaces: composition changed (now 38 parts): added skill modelopt-accessing-mlflow, skill modelopt-benchmark-model-kernels, skill modelopt-compare-results, skill modelopt-day0-release, skill modelopt-debug, skill modelopt-deployment, skill modelopt-evaluation, skill modelopt-launching-evals, skill modelopt-monitor, skill modelopt-ptq, skill modelopt-qad, skill modelopt-quant-recipe-search, skill modelopt-release-cherry-pick, skill modelopt-run-agentx, skill modelopt-speculative-decoding
  3. Community GitHub marketplaces: composition changed (now 23 parts): added agent modelopt-model-distiller
  4. Became a product we track
  5. Community GitHub marketplaces: appeared

Similar plugins

Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.

  • optimization

    Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

    by orchestra-research · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • ai-hub-models

    Qualcomm AI Hub Models authoring skills (onboard, validate-on-device, add-quantization)

    by qualcomm · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • TensorRT-Model-Connect Skills

    Repo-local Codex skills for TensorRT-Model-Connect developer workflows.

    by NVIDIA · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • machine-learning

    ML engineering agents providing expertise in MLOps, model deployment, and inference optimization

    by The Bushido Collective · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • vllm-omni-quantization

    Quantization workflows and troubleshooting for vLLM-Omni.

    by hsliuustc0106 · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • do-machine-learning

    ML engineering agents providing expertise in MLOps, model deployment, and inference optimization

    by The Bushido Collective · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • do-machine-learning-engineering

    ML engineering agents providing expertise in MLOps, model deployment, and inference optimization

    by The Bushido Collective · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • max-skills

    Modular skills for importing, serving, and measuring models on MAX

    by modular · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • unsloth

    Install, operate, and troubleshoot Unsloth Core, Studio, and Desktop for local inference and model training. Use for Unsloth environment setup, LoRA/QLoRA supervised fine-tuning…

    by magnus919 · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • veloq

    Agent Skills for NSys, NCU, and PyTorch profile analysis using the VeloQ CLI.

    by Zihua Wu · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

Similar plugins by marketplace

The same question asked of one marketplace at a time: is there an analog of this plugin there?

Has a listing on Claude Code: claude-plugins-community (5)
  • model-advisor

    Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.

    by Jaace · Plugin bundle

    Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

  • NVIDIA Skills

    Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…

    by NVIDIA · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • fiftyone

    Build high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins.

    by voxel51 · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community · Describes nearly the same job

  • huggingface-skills

    Build, train, evaluate, and use open source AI models, datasets, and spaces.

    by huggingface · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community · Describes nearly the same job

  • harness-evolver

    Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…

    by raphaelchristi · Plugin bundle

    Listed on: Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

Has a listing on Claude Code: claude-plugins-official (5)
  • amd-skills

    AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom…

    by amd · Plugin bundle

    Listed on: Claude Code: claude-plugins-official · Describes nearly the same job

  • NVIDIA Skills

    Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…

    by NVIDIA · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • fiftyone

    Build high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins.

    by voxel51 · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community · Describes nearly the same job

  • huggingface-skills

    Build, train, evaluate, and use open source AI models, datasets, and spaces.

    by huggingface · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude Code: claude-plugins-community · Describes nearly the same job

  • sagemaker-ai

    Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.

    by awslabs · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Community GitHub marketplaces · Describes nearly the same job

Has a listing on Claude: knowledge-work-plugins (5)
  • datarobot-agent-skills

    DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…

    by datarobot-oss · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude: knowledge-work-plugins · Describes nearly the same job

  • qdrant-skills

    Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across…

    by qdrant · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude: knowledge-work-plugins, Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • AI-Firstify

    AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp

    by techwolf-ai · Plugin bundle

    Listed on: Claude: knowledge-work-plugins, Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • qt-development-skills

    Agentic engineering skills for Qt software development — Qt C++/QML code review, QML coding, and Qt C++/QML code documentation.

    by TheQtCompanyRnD · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude: knowledge-work-plugins, Community GitHub marketplaces · Describes nearly the same job

  • langfuse

    Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.

    by langfuse · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Claude: knowledge-work-plugins, Claude Code: claude-plugins-community · Describes nearly the same job

Has a listing on Codex: openai-curated (openai/plugins) (5)
  • NVIDIA

    Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…

    by NVIDIA · Plugin bundle

    Listed on: Codex: openai-curated (openai/plugins) · Describes nearly the same job

  • Plugin Eval

    Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.

    by OpenAI Codex · Plugin bundle

    Listed on: Codex: openai-curated (openai/plugins) · Describes nearly the same job

  • OpenAI Developers

    Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.

    by OpenAI · Plugin bundle

    Listed on: Codex: openai-curated (openai/plugins) · Describes nearly the same job

  • crowdstrike-falcon-foundry

    CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…

    by CrowdStrike · Plugin bundle

    Listed on: Claude Code: claude-plugins-official, Codex: openai-curated (openai/plugins), Copilot CLI: github/awesome-copilot, Claude Code: claude-plugins-community · Describes a similar job

  • Build iOS Apps

    Build iOS apps with workflows for App Intents, SwiftUI UI work, Simulator mirroring in the Codex in-app browser, performance profiling, leak investigation, and simulator debugging.

    by OpenAI · Plugin bundle

    Listed on: Codex: openai-curated (openai/plugins) · Describes a similar job

Has a listing on Community GitHub marketplaces (5)
  • optimization

    Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

    by orchestra-research · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • ai-hub-models

    Qualcomm AI Hub Models authoring skills (onboard, validate-on-device, add-quantization)

    by qualcomm · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • TensorRT-Model-Connect Skills

    Repo-local Codex skills for TensorRT-Model-Connect developer workflows.

    by NVIDIA · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • machine-learning

    ML engineering agents providing expertise in MLOps, model deployment, and inference optimization

    by The Bushido Collective · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • vllm-omni-quantization

    Quantization workflows and troubleshooting for vLLM-Omni.

    by hsliuustc0106 · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

Has a listing on Copilot CLI: github/awesome-copilot (5)
  • ai-team-orchestration

    Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.

    by Denis Evdokimov · Plugin bundle

    Listed on: Copilot CLI: github/awesome-copilot · Describes nearly the same job

  • arize-ax

    Arize AX platform skills for LLM observability, evaluation, and optimization. Includes trace export, instrumentation, datasets, experiments, evaluators, AI provider integrations…

    by Arize AI · Plugin bundle

    Listed on: Copilot CLI: github/awesome-copilot · Describes nearly the same job

  • phoenix

    Phoenix AI observability skills for LLM application debugging, evaluation, and tracing. Includes CLI debugging tools, LLM evaluation workflows, and OpenInference tracing…

    by Arize AI · Plugin bundle

    Listed on: Copilot CLI: github/awesome-copilot · Describes nearly the same job

  • edge-ai-tasks

    Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai

    by Awesome Copilot Community · Plugin bundle

    Listed on: Copilot CLI: github/awesome-copilot · Describes nearly the same job

  • radius

    Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.

    by radius-project · Plugin bundle

    Listed on: Copilot CLI: github/awesome-copilot · Describes nearly the same job

Has a listing on Copilot CLI: github/copilot-plugins (5)
  • microsoft-365-agents-toolkit

    Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.

    by microsoft · Plugin bundle

    Listed on: Copilot CLI: github/copilot-plugins · Describes nearly the same job

  • model-apps

    Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…

    by microsoft · Plugin bundle

    Listed on: Copilot CLI: github/copilot-plugins · Describes nearly the same job

  • fabric-skills

    Complete bundle: all Microsoft Skills for Fabric for developers and consumers.

    by microsoft · Plugin bundle

    Listed on: Copilot CLI: github/copilot-plugins · Describes nearly the same job

  • code-apps-preview

    Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.

    by microsoft · Plugin bundle

    Listed on: Copilot CLI: github/copilot-plugins · Describes nearly the same job

  • build-perf-cpp

    Analyze MSVC build performance using vcperf.exe and ETL traces.

    by Ion Todirel and Eve Silfanus · Plugin bundle

    Listed on: Copilot CLI: github/copilot-plugins · Describes nearly the same job

Has a listing on Cursor: cursor/plugins (5)
  • pstack

    if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.

    by Lauren Tan · Plugin bundle

    Listed on: Cursor: cursor/plugins · Describes nearly the same job

  • Orchestrate

    Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.

    by Cursor · Plugin bundle

    Listed on: Cursor: cursor/plugins · Describes nearly the same job

  • Cursor SDK

    Build apps, scripts, and automations with the TypeScript SDK.

    by Cursor · Plugin bundle

    Listed on: Cursor: cursor/plugins · Describes nearly the same job

  • Origin Apps

    Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…

    by Cursor · Plugin bundle

    Listed on: Cursor: cursor/plugins · Describes nearly the same job

  • Advisor

    Consult a stronger model before major decisions, when stuck, and before declaring done.

    by Cursor · Plugin bundle

    Listed on: Cursor: cursor/plugins · Describes nearly the same job

Has a listing on Docker MCP Catalog (5)
  • Opik

    Read and score Opik traces, experiments, datasets and prompts from your AI assistant.

    by comet-ml · MCP server

    Listed on: Official MCP Registry, Docker MCP Catalog, PyPI (MCP servers) · Describes nearly the same job

  • Zen

    Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.

    by BeehiveInnovations · MCP server

    Listed on: Docker MCP Catalog · Describes nearly the same job

  • Arm MCP Server

    Official Arm MCP server for code migration, optimization, and Arm architecture guidance

    by arm · MCP server

    Listed on: Official MCP Registry, Docker MCP Catalog · Describes nearly the same job

  • Novita

    Seamless interaction with Novita AI platform resources.

    by novitalabs · MCP server

    Listed on: Docker MCP Catalog · Describes nearly the same job

  • Postman MCP Server

    Give your AI agents trusted access to the full Postman platform.

    by postman.com · MCP server

    Listed on: Official MCP Registry, Docker MCP Catalog, npm registry (MCP servers) · Describes nearly the same job

Has a listing on Official MCP Registry (5)
  • EcoCompute Should-I-Quantize Estimator

    Energy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis.

    by hongping-zh · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • crit

    Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.

    by crit-labs · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • mcp com.synqtune/mcp

    Fine-tune a small model on your data and benchmark it against your LLM API, in your AWS account.

    by synqtune.com · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • Grandet

    Cheapest API for any model across official, inference and relay providers; find free credits

    by hanzohanzhe · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • DEEPBOM

    Browser-local and CLI static evidence for deployed AI model artifacts.

    by JunHwan-Kwon · MCP server

    Listed on: Official MCP Registry, npm registry (MCP servers) · Describes nearly the same job

Has a listing on PyPI (MCP servers) (5)
  • AlbumentationsX MCP

    AlbumentationsX MCP for batch previews, compare preview runs, segmentation masks, and exports.

    by dKosarevsky · MCP server

    Listed on: Official MCP Registry, PyPI (MCP servers) · Describes nearly the same job

  • @hanzo/mcp

    Hanzo MCP Server - Unified tool surface with AI, cloud control, vector search, and multi-framework UI

    by @hanzo · MCP server

    Listed on: npm registry (MCP servers), PyPI (MCP servers) · Describes nearly the same job

  • mcp-client-for-ollama

    MCP Client for Ollama - A client for connecting to Model Context Protocol servers using Ollama

    by jonigl · MCP server

    Listed on: PyPI (MCP servers) · Describes nearly the same job

  • Opik

    Read and score Opik traces, experiments, datasets and prompts from your AI assistant.

    by comet-ml · MCP server

    Listed on: Official MCP Registry, Docker MCP Catalog, PyPI (MCP servers) · Describes nearly the same job

  • offline-mcp io.github.gabrielmahia/offline-mcp

    Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.

    by gabrielmahia · MCP server

    Listed on: Official MCP Registry, PyPI (MCP servers) · Describes nearly the same job

Has a listing on npm registry (MCP servers) (5)
  • llm-checker

    Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system

    by signerless · MCP server

    Listed on: npm registry (MCP servers) · Describes nearly the same job

  • DEEPBOM

    Browser-local and CLI static evidence for deployed AI model artifacts.

    by JunHwan-Kwon · MCP server

    Listed on: Official MCP Registry, npm registry (MCP servers) · Describes nearly the same job

  • Nodegrove VRAM: can I run it?

    Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.

    by nodegrove.io · MCP server

    Listed on: Official MCP Registry, npm registry (MCP servers) · Describes nearly the same job

  • Kosha Model Discovery

    Tells your agent which model to use and what it costs, across 46 providers and local runtimes.

    by sriinnu · MCP server

    Listed on: Official MCP Registry, npm registry (MCP servers) · Describes nearly the same job

  • where-my-hug io.github.bikemeardsley/where-my-hug

    Which parts of an ML need Hugging Face already covers. Every model and dataset checked live.

    by bikemeardsley · MCP server

    Listed on: Official MCP Registry, npm registry (MCP servers) · Describes nearly the same job

Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.

Want this mark on your plugin in our catalog?

Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works

You also get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.

Show up-to-date catalog facts on your website or GitHub README. Choose a live banner or a compact badge.

Live badge preview
See examples and make yours
For your website
Website banner preview
For your README
README badge preview
Open banner builder

Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built