Local AI Models — The Reference for Running AI Locally

Mission Control · Online<br>v2026.08.03

Run<br>AI<br>on<br>your own<br>hardware.

100 open-weight models · cataloged","59 agent frameworks · compared","$199 to $138K · workstation builds","5 to 280 tokens/sec · simulated"]'>

The reference for engineers running AI locally. VRAM math, hardware tradeoffs, model benchmarks, and the agent ecosystem — all in one place. Built to help you understand, not just install.

Pick a destination →<br>Browse 100 models

Models

Agent Frameworks

Hardware Tiers

Live Tools

Scroll

Models

Pages

Hardware tiers

Local · zero cloud

Llama 3.3 70B<br>Qwen3 32B<br>DeepSeek V3.2 671B<br>Phi-4 14B<br>GLM-5 744B<br>Mistral Small 22B<br>Nemotron 3 Super<br>Yi 34B<br>Mixtral 8x22B<br>Llama 4 Scout<br>Qwen2-VL 72B<br>Gemma 3 27B

Destinations

Pick your path. Or take all of them.

Seven tools, one mission — help you decide which model, which hardware, and which framework actually fits what you're building.

I want to…<br>›Browse all 100 models<br>›Build a rig (real prices)<br>›Estimate token cost<br>›Pick an agent framework<br>›Get a recommendation<br>›Mix & match a stack

01 · MODEL INDEX<br>Catalog<br>100

Every open-weight model, in one place.

VRAM, quantization, license, hardware tier, community sentiment. Searchable, filterable, mobile-first. The single reference you bookmark.

Open the Index

PC Builder<br>$3,990

Build a workstation from real parts.

Pick CPU, GPU, RAM, PSU at real April 2026 prices. See the total, see what models fit.

Configure a build

Simulator<br>5 → 80

Feel the speed.

Side-by-side streaming at 5, 25, and 80 tok/s. Pick your hardware, see your real throughput.

Run the simulator

CLAWS Catalog<br>59

The agent-framework ecosystem.

OpenClaw, Hermes, Claw Code, plus 50 coding / orchestration / browser-use frameworks. Filter by category, decide by question.

Explore the catalog

Recommender<br>3 steps

Tell me what you're building.

Use case → hardware → recommended models with reasoning. Skip the analysis paralysis.

Get a recommendation

Stack Builder<br>Fits?

Match models to hardware.

Already have a GPU? See which of the 100 models fit and how fast they run.

Plan a stack

Live Data<br>Live

Community pulse.

Real HuggingFace download counts and likes. What's trending, what's rising, what to watch.

See community data

Reference · Start here

Local AI means running language models on hardware you own instead of calling a company's API. This section explains what that actually means, the honest reasons people choose it, and the tradeoffs to weigh before you commit.

Local AI, explained

What is local AI, and why run models locally?

Open-weight models you download and run on your own hardware, the real reasons people choose them, and where the limits actually are.

Most people meet AI through a hosted service. You open a website or an app, type into a box, and a company's servers do the work and send back an answer. Local AI inverts that arrangement. Instead of renting access to a model that lives in someone else's data center, you download the model's weights (the trained numerical parameters that define how it behaves) and run them on your own computer.

The models that make this possible are usually called open-weight models. Their creators publish the trained parameters under a license that lets you download, run, and often modify them. That is not quite the same as open-source software in the strict sense, because the training data and full training code are not always released, but the finished weights are yours to run. Once the file is on your disk, no account, subscription, or internet connection is required to use it. A local runtime program loads those weights, feeds it your prompt, and streams back the response entirely on your machine.

In practice a local setup has three parts: the model file (commonly distributed in quantized formats like GGUF, which compress the weights so they fit in less memory, as covered in the quantization guide), a runtime or inference engine that executes it, and the hardware it runs on. The model catalog on this site tracks open-weight models and the memory each one needs, so you can see what is actually downloadable and runnable rather than only what is hosted behind an API.

Why people run locally

Privacy<br>Private by default

Your prompts and files never leave the machine. There is no account to create, no usage history tied to your identity, and nothing handed to a third party. For sensitive documents, proprietary code, or personal notes, the data simply stays where it already is.

Cost<br>No per-token fees

Hosted APIs bill per token, so cost scales with how much you use them. A local model carries an up-front hardware and electricity cost but no metered charge per request. Once it runs, you can generate freely without watching a billing meter. Gauge request volume with the token simulator.

Offline<br>Offline and durable

A downloaded model works with no internet at all: on a plane, in an air-gapped lab, or during an outage. It also cannot be...