ComputeSage StackBench
computesage/stackbenchSearch public GPU and LLM benchmark evidence for free, then pay per call for deployment-fit checks, performance predictions, hardware recommendations, and launch configurations.
Score: 100/100
Handshake verified by our own probe.
Tools · 5
$0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests.
$0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.
$0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats.
$0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported.
$0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://computesage.com/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"computesage_stackbench": {
"url": "https://computesage.com/mcp",
"transport": "http"
}
}
}