AI Compute Radar

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.

{
  "type": "object",
  "properties": {
    "limit": {
      "description": "How many models to return (default 12).",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "slug": {
      "description": "Return a single model by slug.",
      "type": "string"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

{
  "type": "object",
  "properties": {
    "hardware": {
      "type": "string",
      "description": "Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb."
    },
    "model": {
      "description": "Restrict to one model slug.",
      "type": "string"
    },
    "context": {
      "description": "Context length in tokens (default 8192).",
      "type": "integer",
      "minimum": 512,
      "maximum": 1048576
    },
    "kv": {
      "description": "KV-cache quantization (default f16).",
      "type": "string",
      "enum": [
        "f16",
        "q8_0",
        "q4_0"
      ]
    }
  },
  "required": [
    "hardware"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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 Azure and Oracle Cloud pay-as-you-go list prices per GPU-hour, each with the 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.

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

{
  "type": "object",
  "properties": {
    "week": {
      "description": "ISO week label of a past issue, e.g. 2026-w37 (default: the current issue).",
      "type": "string",
      "pattern": "^\\d{4}-w\\d{2}$"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}