Scottcjn/llama-cpp-power8
AltiVec/VSX optimized llama.cpp for IBM POWER8
This project helps you run large language models (LLMs) like LLaMA and DeepSeek directly on your older IBM POWER8 server hardware. It takes trained LLM models and processes them much faster on POWER8 than standard methods, letting you use your existing powerful servers for AI tasks. If you own or manage IBM POWER8 systems and want to perform AI inference locally, this tool is for you.
Use this if you need to run large language models efficiently on your existing IBM POWER8 server infrastructure, rather than relying on cloud services or newer, more expensive hardware.
Not ideal if you don't have access to IBM POWER8 hardware or are looking for a solution compatible with x86, ARM, or NVIDIA GPU systems.
Stars
47
Forks
10
Language
C
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Scottcjn/llama-cpp-power8"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
containers/ramalama
RamaLama is an open-source developer tool that simplifies the local serving of AI models from...
av/harbor
One command brings a complete pre-wired LLM stack with hundreds of services to explore.
RunanywhereAI/runanywhere-sdks
Production ready toolkit to run AI locally
runpod-workers/worker-vllm
The RunPod worker template for serving our large language model endpoints. Powered by vLLM.
foldl/chatllm.cpp
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)