MCP serverdev.aicomputeradar/ai-compute-radar

Which open models fit your GPU or Mac, measured.

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

UNRATEDActivestreamable-httpaicomputeradar.dev

Overview

Score?

UNRATED 0.576

of what a free look can see, on 17 looks

Looks

last 36 min ago

Tools

changed 1 day ago

URL

aicomputeradar.dev/api/mcp

streamable-http

Says it is

ai-compute-radar 1.2.0

protocol 2025-06-18

In the record since

15 days ago

0median 0.606 · this server 0.576 · highest on record 0.8561

The tools this server lists, read out of the definition it returned
Tool	Schema
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 ve	input · no output
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 m	input · no output
list_hardware Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.	input · no output
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	input · no output
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), wi	input · no output

Verify it yourselfnpx teppi-check https://aicomputeradar.dev/api/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M2W3S2AMBCE3B9VEKQY8KFA5