This month, we discuss some of the options and issues about running your own Generative AI at home. As well as avoiding privacy issues with online Generative AI and reducing AI bills, it’s always fun to have a tinker to find out what’s possible. Will include several demos.
If you aren’t a member, it’s free to join here https://u3acommunities.org/subscribe-to-computing-forum/.
Plenty of time is reserved for discussions.
20th May 2025 at 3pm UK
the slides were :
The recording was :
The references were :
- Llama.cpp – https://github.com/ggml-org/llama.cpp
- Ollama – https://ollama.com/
- LM Studio – https://lmstudio.ai/
- Jan – https://jan.ai/
- Llamafile – https://github.com/Mozilla-Ocho/llamafile
- Gpt4all – https://www.nomic.ai/gpt4all
- Rknn-llm – https://github.com/airockchip/rknn-llm
- LocalAI – https://localai.io/
- Hailo – https://hailo.ai/
- Jellybox – https://jellybox.com/
- Stable-diffusion.cpp – https://github.com/leejet/stable-diffusion.cpp
- Open web UI – https://docs.openwebui.com/
- AUTOMATIC1111 – https://github.com/AUTOMATIC1111/stable-diffusion-webui
- Home assistant – https://www.home-assistant.io/integrations/ollama
- Diffusion LLM – https://www.inceptionlabs.ai/
- Lego GPT – https://avalovelace1.github.io/LegoGPT/ (needs academic licence)