AI Compute Radar

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Measured statistics

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AI Compute Radar": {
      "url": "https://aicomputeradar.dev/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• 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.

  Parameters:

  • slug — string — Return a single model by slug.
  • limit — integer — How many models to return (default 12).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • hardware (required) — string — Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb.
  • kv — string — KV-cache quantization (default f16).
  • model — string — Restrict to one model slug.
  • context — integer — Context length in tokens (default 8192).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world 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.

  Parameters:

  • week — string — ISO week label of a past issue, e.g. 2026-w37 (default: the current issue).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.