AI Compute Radar
Server Details
Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool targets a distinct resource: hardware catalog (list_hardware), fit computation (find_fit), current market prices (gpu_prices), daily price rows (price_history), model heat ranking (trending_models), and a curated weekly issue (weekly_pick). The only near-pair, gpu_prices vs price_history, is explicitly separated by descriptions that state history is the source rows and never blended with current medians. No two tools appear to do the same thing.
Names mix verb_noun (find_fit, list_hardware) with noun phrases (gpu_prices, price_history, trending_models, weekly_pick). Each name is readable and meaningful, but there is no single predictable pattern an agent can generalize from. This is a mixed convention rather than a consistent one.
Six tools is well-scoped for a compute-market intelligence server. Each tool covers a distinct lane (catalog, fit, pricing snapshot, price history, model trends, editorial pick) with no filler. Pairs naturally into three coherent capabilities.
The surface covers the full loop for its stated purpose: discover hardware, test fit, read current and historical prices, rank models, and get a weekly pick. Minor gaps remain, such as no direct lookup of a single model's full profile (trending_models returns a ranked list) and no way to query a specific GPU class outside the price feeds. These are workaroundable but noticeable.
Publisher details
- Operator
- AI Compute Radar, a free, non-commercial information project operated privately from Germany · Publisher source
- Operator website
- https://aicomputeradar.dev · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://aicomputeradar.dev/developers · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- None: no account, no API key, free. Best-effort rate limit of 60 requests per minute per client; responses cached for five minutes. Data is CC BY 4.0 with the attribution text carried in every response. · Publisher source
Available Tools
6 toolsfind_fitFind models that fit a machineAInspect
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.
Inputs: hardware (required), kv, model, context.
gpu_pricesGPU rental pricesAInspect
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.
Inputs: no named parameters.
list_hardwareList hardware profilesAInspect
Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.
Inputs: no named parameters.
price_historyGPU rental price historyBInspect
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, Lambda, Nebius, CoreWeave, Hyperstack) carry the posted price. Each row says which kind it is; never blend the two. Describes what prices did; it never forecasts.
Inputs: gpu, days, source.
trending_modelsTrending modelsAInspect
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.
Inputs: slug, limit.
weekly_pickPick of the weekAInspect
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.
Inputs: week.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Find open-weight AI models that fit your hardware, with weight sizes, memory and sources.
Related MCP Servers
- AlicenseAqualityBmaintenanceLLM deployment planner: given a model and a GPU, answers will it fit, will it hit your SLO, and what will it cost. Sizes VRAM and KV-cache from the model's real architecture, and labels every number measured, estimated, or unknown.51,118 PyPI3MIT
- AlicenseNot gradedqualityBmaintenanceWill this AI model fit on your Mac?54 npm9MIT
- AlicenseAqualityDmaintenanceGive your AI assistant real-time LLM/VLM knowledge. Pricing, benchmarks, and recommendations — updated every hour, not every training cycle.490 npm2MIT
- AlicenseAqualityBmaintenanceChecks whether an open-weight LLM fits your GPU: VRAM for weights, KV cache and overhead at each quantisation, a tokens-per-second ceiling, the longest context that fits, and what would work instead when it doesn't. Reads any Hugging Face repo's config.json. Free, read-only, no API key.6MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.