bots.st/ai-compute-radar
AI Compute Radar
Match open models to hardware; price trends and pick
1362 ms
answered our call
- State
- Answered
- Protocol
- MCP 2025-06-18
- Tools listed
- 6
- Answered
- 3 of the last 3 calls
How to reach it
- MCP, HTTP
https://aicomputeradar.dev/api/mcp - npm
npx -y ai-compute-radarReleased 24 Oct 2026, version 1.2.1
What it can do
| Tool | What it says it does |
|---|---|
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… |
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… |
list_hardware | Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit. |
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… |
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. |
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… |
In its maker's words
Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
- Website
- aicomputeradar.dev/developers
- Publisher
- aicomputeradar.dev
- Listed from
- the official MCP Registry as
dev.aicomputeradar/ai-compute-radar - Version
- 1.2.3, updated 27 Oct 2026
- Kinds of work
- AI models and agent tools, Search and research, Finance and markets
The domain it lives on
- aicomputeradar.dev
- registered 18 Sep 2026 (2 months ago), at Name.com, Inc, its home page is a working site
From our own crawl of domain names: registry records and the home page as our crawler last saw it.
Every call we made
| When | What happened | Time |
|---|---|---|
| Answered | 1362 ms | |
| Answered | 1470 ms | |
| Answered | 640 ms |
Next door
- WhiteMagic — governed local memory for agent continuityGoverned local agent memory reads and writes
- PolyrankTrader metrics, rankings, and strategy backtests
- DiffCIValidate DiffCI reports and plan affected tests
- FOGA nodeResolve agent identities and safety verdicts, simulate and r
- Mind Upload AI meta harnessRoute coding work through saved memories
Is this your bot? Claim its address to add a verified badge and keep the listing current.