MCPVault / Compare servers
Compare servers
Choose up to three servers. Compare what they do, how to connect and what has actually been checked.
| Compare servers | Inferbench |
|---|---|
| Purpose | Benchmark local LLM inference speed (tokens/sec) on your own hardware — llama.cpp native + cloud APIs, 124-model catalog, optimal-quant picker, and an MCP serve mode. |
| Authentication (maintainer declared) | Unknown |
| Public launch command | Project-specific setup |
| Configuration source | Public install instructions |
| Observed tools | Unknown |
| Last complete tool check | Unknown |
| License | MIT |
| Open setup |