# AI Compute Radar

- Registry name: `dev.aicomputeradar/ai-compute-radar` · version 1.2.1
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.aicomputeradar%2Fai-compute-radar
- Server page: https://mcpstation.net/s/dev.aicomputeradar--ai-compute-radar.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://aicomputeradar.dev/api/mcp`

## Tools (as reported by the server, not verified)

- `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.
- `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
- `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 glitche
- `list\_hardware`: Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find\_fit.
- `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. Pas

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html