# model-optimizer

Documentation | Roadmap | NVIDIA Model Optimizer (referred to as Model Optimizer, or ModelOpt) is a library comprising state-of-the-art model optimization techniques including quantization, pruning, Neural Architecture Search (NAS), distillation, speculative

- Tier: Indexed (plain plugin)
- Category: Machine Learning
- Page: https://www.flowy.sh/listings/nvidia-model-optimizer
- Source: https://github.com/nvidia/model-optimizer
- Price: free and open source

## Summary
model-optimizer is a Claude Code plugin with 16 hand-picked skills for machine learning work, indexed on Flowy. Install it with the command on its page. It includes accessing-mlflow, benchmark-model-kernels, common. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

## Install (Claude Code)
```
/plugin marketplace add nvidia/model-optimizer
/plugin install modelopt@modelopt
```

## Skills
- accessing-mlflow
- benchmark-model-kernels
- common
- compare-results
- day0-release
- debug
- deployment
- evaluation
- launching-evals
- monitor
- ptq
- qad
- quant-recipe-search
- release-cherry-pick
- run-agentx
- speculative-decoding

## FAQ

### What is model-optimizer?
Documentation | Roadmap | NVIDIA Model Optimizer (referred to as Model Optimizer, or ModelOpt) is a library comprising state-of-the-art model optimization techniques including quantization, pruning, Neural Architecture Search (NAS), distillation, speculative

### How do I install model-optimizer?
Run these in Claude Code: /plugin marketplace add nvidia/model-optimizer then /plugin install modelopt@modelopt. Then prompt normally.

### Does model-optimizer auto-invoke its skills?
Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

### Is model-optimizer free?
Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.