inferbench

Level FSource

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.

⭐ 2Development ToolsPythonRepo ↗Updated 2026-10-25

Installation

View source repo →

Related servers

REA⭐ 419.9k · Development Tools逆向工程一体化 MCP：把 Ghidra、IDA、Hopper、JADX、Frida、ADB、浏览器等工具统一封装，Agent 无需源码即可分析二进制、App、gemini-cli⭐ 108.7k · Development ToolsAn open-source AI agent that brings the power of Gemini directly into your termiawesome-mcp-servers⭐ 97.2k · Development ToolsA collection of MCP servers.claude-flow⭐ 78.2k · Development ToolsAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enFront-End Checklist⭐ 74.5k · Development ToolsReview frontend code and live pages against 386 quality-gated web development rucline⭐ 71.2k · Development ToolsAutonomous coding agent as an SDK, IDE extension, or CLI assistant.