MCP servers
inferbench
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Remotes
This server publishes no hosted endpoint. Run one of its packages locally.
Packages
inferbench-cli · pypi 0.1.7 · stdio
claude mcp add --transport stdio inferbench -- uvx inferbench-cli==0.1.7Server details
- Registry name
- io.github.RudrenduPaul/inferbench
- Version
- 0.1.7
- Registry status
