Connection check
verified live · 20h ago
stackbench
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Tools
5
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http
Last checked
20h ago
Tools & capabilities
5 toolsRead from the running server on 20h ago.
check_deployment_fit
read-only
model*engineconcurrencymax_evidencequantizationcontext_length*
+1
$0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence. $0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.
generate_launch_config
read-only
model*runtime*objectivebatch_sizeconcurrencyubatch_size
+13
$0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred. $0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.
predict_performance
read-only
model*enginebatch_sizeconcurrencyubatch_sizemax_evidence
+9
$0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats. $0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats.
recommend_deployment
read-only
modemodel*engineobjectivetco_yearsbatch_size
+36
$0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported. $0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported.
search_evidence
read-only
limitquery*