rtk vs PowerInfer

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

rtkPowerInfer
TaglineCLI proxy reducing LLM token consumption by 60-90%High-speed Large Language Model Serving for Local Deployment
Stars69k9.6k
Forks4.3k585
Open issues1.5k129
LanguageRustC++
LicenseApache-2.0MIT
Last pushedJul 7, 2026May 11, 2026
CategoriesInference & Serving, Developer ToolsInference & Serving, LLM Frameworks

rtk

RTK is a high-performance CLI proxy written in Rust that significantly reduces the number of tokens consumed by Large Language Models (LLMs) when executing common development commands.

Rust

PowerInfer

PowerInfer is a CPU/GPU LLM inference engine that utilizes activation locality to optimize performance on consumer-grade GPUs and CPUs.

C++