Tools & Regulation
Groq (inference platform)
Groq runs LLM inference on custom LPU chips – at hundreds of tokens per second. Models, speed, and typical use cases at a glance.
3 articles with this tag
Groq runs LLM inference on custom LPU chips – at hundreds of tokens per second. Models, speed, and typical use cases at a glance.
Open source LLMs can be downloaded, self-hosted, and adapted. Examples, benefits, limitations – and why the licence makes the difference.
Self-hosted AI means language models run on company hardware. Requirements, tools like Ollama and vLLM, benefits and limits at a glance.