AI Compute Radar
Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"ai-compute-radar": {
"url": "https://aicomputeradar.dev/api/mcp"
}
}
}リモートエンドポイント
https://aicomputeradar.dev/api/mcpstreamable-httpできること
ツール一覧
ツール（5）
⚪trending_models(limit, slug)
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.
入力スキーマ
{
"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"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢find_fit(hardware, model, context, kv)
Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.
入力スキーマ
{
"type": "object",
"properties": {
"hardware": {
"type": "string",
"description": "Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb."
},
"model": {
"description": "Restrict to one model slug.",
"type": "string"
},
"context": {
"description": "Context length in tokens (default 8192).",
"type": "integer",
"minimum": 512,
"maximum": 1048576
},
"kv": {
"description": "KV-cache quantization (default f16).",
"type": "string",
"enum": [
"f16",
"q8_0",
"q4_0"
]
}
},
"required": [
"hardware"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢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 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.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_hardware
Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}⚪weekly_pick(week)
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.
入力スキーマ
{
"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"
}コミュニティ
エビデンス