# AI Model Radar

> Measured signals for the AI-model and compute market: Hugging Face
> trending and downloads, OpenRouter API prices, Vast.ai GPU rental rates —
> collected automatically several times a day — plus deterministic engines
> that compute which open models fit which hardware and what a workload
> costs across cloud API, owned hardware and rented GPUs. Every figure is a
> measured reading with a timestamp, a sourced vendor fact, or a declared
> assumption; the methodology page states the rules.

## Core pages

- [Model board](https://aimodelradar.dev/): open models ranked by measured Hugging Face trending score, with API prices and download counts
- [Local AI finder](https://aimodelradar.dev/local): which models run on which GPU or Mac, from measured GGUF sizes and published attention shapes
- [Cost calculator](https://aimodelradar.dev/costs): the same model priced three ways — cloud API, owned hardware, rented GPU
- [GPU rental prices](https://aimodelradar.dev/compute/rent): median verified $/h per GPU class with daily history
- [Stack builder](https://aimodelradar.dev/stack): a deterministic local/cloud stack recommendation from seven questions
- [Local AI tools](https://aimodelradar.dev/tools): curated runtimes (Ollama, LM Studio, llama.cpp, Jan, Open WebUI)
- [Hardware hub](https://aimodelradar.dev/hardware): every tracked GPU and Mac with how many models run comfortably, plus the guides below
- [Local AI on a budget](https://aimodelradar.dev/hardware/budget): which used and entry-level GPUs genuinely run local models, what to avoid, buying checklist — fit counts computed, no street prices
- [Glossary](https://aimodelradar.dev/glossary): local-AI terms in plain language (GGUF, quantization, KV cache, unified memory, MoE, …) — one page per term under https://aimodelradar.dev/glossary/<slug>; Spanish edition under https://aimodelradar.dev/es/glossary, Portuguese under https://aimodelradar.dev/pt/glossary (same slugs, hreflang-linked)

## How the numbers are made

- [Methodology](https://aimodelradar.dev/methodology): what is measured, what is computed, what is assumed — and what this site refuses to publish

## Machine access

- [JSON API](https://aimodelradar.dev/api/v1): read-only, no keys, CORS-open — models ranked by Heat Score with measured signals (https://aimodelradar.dev/api/v1/models), hardware-fit verdicts (https://aimodelradar.dev/api/v1/fit?hardware=rtx-4090), GPU rental prices (https://aimodelradar.dev/api/v1/prices), hardware profiles (https://aimodelradar.dev/api/v1/hardware). OpenAPI 3.1: https://aimodelradar.dev/api/v1/openapi.json
- [MCP server](https://aimodelradar.dev/api/mcp): Streamable HTTP, stateless — tools trending_models, find_fit, gpu_prices, list_hardware. Setup and terms: https://aimodelradar.dev/developers
- Every response carries meta.source (live = measured, fallback = demo fixtures) and meta.collectedAt. Data is CC BY 4.0 — attribute "AI Model Radar (https://aimodelradar.dev)".

## Notes for agents

- Per-device pages exist at https://aimodelradar.dev/local/gpu/<slug> for every tracked GPU and Apple Silicon machine.
- Data freshness is visible on every section; the health endpoint at https://aimodelradar.dev/api/health reports collection staleness as JSON.
- Outbound model links resolve via https://aimodelradar.dev/go/huggingface?p=<repo>; GGUF links point at the exact quantized file our memory figures were measured from.
- Corrections, feedback, missing models or GPUs: aimodelradar@gmail.com (see https://aimodelradar.dev/legal/imprint#contact). A correction that survives checking updates the data.