IK

ik_llama.cpp

Performance-focused fork of llama.cpp with new quant types

Local LLM Runners ★ 3k stars Hard setup MIT

ik_llama.cpp is a fork of llama.cpp maintained by ikawrakow that adds optimized CPU and CUDA kernels, additional quantization formats, and improved performance for mixture-of-experts models. It targets users running large local models on commodity hardware.

Key features

  • New quantization types
  • Optimized MoE inference
  • CPU and CUDA kernels
  • OpenAI-compatible server

Strengths

  • Released under the MIT license
  • Active community (3k GitHub stars)
  • Written in C++

ik_llama.cpp replaces

Compare ik_llama.cpp

25 head-to-head comparisons.

Similar local llm runners apps