Xiu
VS
The bears are loading the page…
XiuZon AI review community · two bears are duelling
Back to AI Innovation
AI InnovationOpen Source Open source
llama.cpp
GGML Org
Run large model inference on any machine
Visit projectAbout this project
A pure C/C++ implementation of GGML quantization and inference, it runs on CPU even without CUDA, using Metal on Apple Silicon and Vulkan / CUDA on discrete GPUs. The project also defines the GGUF model format and ships llama-server, and many local deployment stacks are built on top of it.
Inference engineQuantizationLocal deployment