AI Compute Radar

dev.aicomputeradarPublished by aicomputeradar.devOfficial publisherv1.2.3Updated Oct 29, 2026

Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureAI & ML

Overview

AI-generated overview

Read-only AI model and GPU data: model heat rankings, hardware-fit verdicts, GPU rental prices and a weekly pick.

What you can do
  • Rank tracked AI models by a measured Heat Score, with raw signals and local-run facts
  • Check which models fit a given GPU or Mac, with verdicts and plain-language reasons
  • Look up median GPU rental prices per class, plus the Rent Index trend
  • Read daily price history per GPU class and source for up to 90 days
  • List the curated GPU and Mac profiles the fit engine knows
  • Get the current weekly pick with its frozen readings and fit ladder
When to use it
Useful when choosing an open model for a specific GPU or Mac, comparing GPU rental costs, or following which models are gaining momentum. It is a read-only reference source, not a benchmark or speed-testing tool.
Requirements
Runs as a remote streamable HTTP endpoint or as a local npm package via npx (Node.js). No authentication, environment variables or headers are declared. Network access is needed to fetch the data.
Before you install
Results carry meta.source, which can be live or fallback demo fixtures, so check it before quoting numbers. Data is measured, not forecast, and contains no speed figures or benchmarks. Attribution under CC BY 4.0 is requested when reusing the data.

Installation

In SourceWeft

  1. Open AI Compute Radar in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.aicomputeradar%2Fai-compute-radar/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "ai-compute-radar": {
      "type": "http",
      "url": "https://aicomputeradar.dev/api/mcp"
    }
  }
}

Tools

6

find_fit

Find models that fit a machine

Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.

Parameterskvmodelcontexthardwarerequired

gpu_prices

GPU rental prices

Median verified on-demand rental price per GPU class on Vast.ai (USD per hour), with min/p75 and offer counts, the collection timestamp, and per class the Rent Index: this week's median against last week and against the first week collected, a trend word, and the days excluded as marketplace glitches, plus RunPod's lowest posted on-demand price per class (a list price, not a median), Clore.ai's median for the same class (a second marketplace, never blended), and the AWS, Azure and Oracle Cloud pay-as-you-go list prices per GPU-hour, each with the instance type, VM size or bare-metal shape the price sits in (list prices, read four times a day, no statement about capacity). The index describes what prices did; it never forecasts.

Takes no parameters.

price_history

GPU rental price history

Daily price history per GPU class and source, up to 90 days: the rows the Rent Index and the 30-day range are computed from. Marketplace days (Vast.ai, Clore.ai) are medians over the day's counted hourly medians with min, p75 and offer count; list-price days (RunPod, AWS, Azure, Oracle Cloud, Lambda, Nebius, CoreWeave, Hyperstack) carry the posted price. Each row says which kind it is; never blend the two. Describes what prices did; it never forecasts.

Parametersgpudayssource

list_hardware

List hardware profiles

Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.

Takes no parameters.

weekly_pick

Pick of the week

The current pick of the week: one tracked model chosen by a published rule (largest counted Heat Score rise among models that run comfortably on a consumer card of up to 24 GB), with the numbers frozen at selection time, a device-by-device fit ladder and the written report including its caveats. Pass week (e.g. 2026-w37) for a past issue. issue is null until the first issue is published.

Parametersweek

Version history

4
  1. v1.2.3LatestOct 29, 2026
  2. v1.2.2Oct 24, 2026
  3. v1.2.1Oct 22, 2026
  4. v1.2.0Sep 18, 2026

Score

65% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.