llama.cpp
ggml · Open Source · Trust 91The fast C/C++ inference engine behind many local AI apps — runs even on laptops without a GPU.
Build it yourself · Alternatives
Ollama by Ollama belongs to the area “Build it yourself” on OROBO. Here are 8 alternatives from the same area, first 7 with the same goals. Every entry is checked automatically every day (origin, code patterns, licence, maintenance, reachability); OROBO does not check whether software fits your purpose.
The fast C/C++ inference engine behind many local AI apps — runs even on laptops without a GPU.
The standard library for thousands of open models across text, vision and audio.
Framework for chaining models, tools and data into AI applications.
High-throughput serving engine for LLMs — for running your own AI infrastructure.
Speech recognition with OpenAI's Whisper model — local, fast, no upload.
TypeScript toolkit for adding AI features to web apps — provider-agnostic.
FLUX image and video models via pay-as-you-go API, plus open weights to self-host.
Real-time voice models and LLM inference for apps and games, with very low-latency speech via API.
All software in “Build it yourself” with filters by price, offline use and difficulty.