AI Compute Radar

dev.aicomputeradar/ai-compute-radarVersion 1.2.3

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

Status

Responds189 msNov 14, 2026, 14:25 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:25 UTC
Latency: 189 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://aicomputeradar.dev/api/mcpResponds189 msNov 14, 2026, 14:25 UTC

No sign-in

Claude Code

claude mcp add --transport http ai-compute-radar https://aicomputeradar.dev/api/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: ai-compute-radar
Remote MCP server URL: https://aicomputeradar.dev/api/mcp

Cursor

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

VS Code

code --add-mcp '{"name":"ai-compute-radar","type":"http","url":"https://aicomputeradar.dev/api/mcp"}'

Streamable HTTP

npm: ai-compute-radar 1.2.1

Package only

npm (npx)

claude mcp add ai-compute-radar -- npx -y ai-compute-radar@1.2.1

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

6 tools

Tools of AI Compute Radar
	Description		Read-only	Idempotent	Open world
`find_fit`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.	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.	Not declared	Not declared	Not declared	Not declared
`gpu_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.	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.	Not declared	Not declared	Not declared	Not declared
`list_hardware`Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.	Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.	Not declared	Not declared	Not declared	Not declared
`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.	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.	Not declared	Not declared	Not declared	Not declared
`trending_models`Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have heat=null and rank after scored ones.	Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have heat=null and rank after scored ones.	Not declared	Not declared	Not declared	Not declared
`weekly_pick`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.	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.	Not declared	Not declared	Not declared	Not declared

Details

Registry status: Active
Published: Oct 27, 2026
Updated: Oct 27, 2026
Website: https://aicomputeradar.dev/developers⁠ (opens in a new tab)
Repository: Not given
Categories (suggested): AI modelsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing