Hacker News
- Self-hosting an AI (LLM) chatbot without going broke https://blog.kronis.dev/tutorials/self-hosting-an-ai-llm-chatbot-without-going-broke 2 comments
- Self-hosted offline transcription and diarization service with LLM summary https://github.com/transcriptionstream/transcriptionstream 37 comments
- Self-Hosting GPU-Accelerated LLM (Mistral 7B) on Kubernetes (EKS) https://medium.com/prodigy-engineering/running-gpu-accelerated-llm-workloads-on-eks-9928c07d30ea 3 comments
- No One wants to host their own LLM Model or Blockchain Node https://olshansky.substack.com/p/no-one-wants-to-host-their-own-llm 2 comments
- Benchmarks and comparison of LLM AI models and API hosting providers https://artificialanalysis.ai 70 comments
- Why host your own LLM? http://marble.onl/posts/why_host_your_own_llm.html 132 comments
- Show HN: Hosted Motorhead (LLM Memory Server) https://getmetal.io/posts/06-hosted-motorhead 3 comments
Lobsters
- LLM CLI tool now supports self-hosted language models via plugins https://simonwillison.net/2023/Jul/12/llm/ 6 comments ai , python
- Why host your own LLM? http://marble.onl/posts/why_host_your_own_llm.html 2 comments ai
- Self-hosted RSS/ATOM reader with LLM-generated tags, scoring, filtering, and sorting https://github.com/Tiendil/feeds.fun 2 comments python
- Introducing Envelofy: Self-Hosted Envelope Budgeting with AI Insights and a (Glitchy) LLM Assistant https://github.com/nicholasjemblow/envelofy 7 comments selfhosted
- TurboPilot: A self-hosted Copilot clone that runs a code-completion LLM on your CPU https://github.com/ravenscroftj/turbopilot 32 comments selfhosted
- Self-hosting Meta's LLM Llama 2 Guide https://github.com/yusyel/guides/tree/master/Takeoff%20Server#self-hosting-large-language-models-and-sharing-with-cloudflare-tunnel 5 comments selfhosted
- Danswer: Self-Hosted way to connect an LLM of your choice to Docs, Websites, and SaaS tools like Google Drive, Notion, Bookstack, Zulip, etc. https://github.com/danswer-ai/danswer 2 comments selfhosted
- Homemade LLM Hosting with Two-Way Voice Support using Python, Transformers, Qwen, and Bark https://herahaven.ai/blog/homemade-llm-hosting-with-two-way-voice-support-using-python-transformers-qwen-and-bark/ 4 comments python
- Ollama - super easy to host local LLM https://github.com/jmorganca/ollama 11 comments selfhosted
- LLM Pal: AI inside Emacs via LSP. Locally hosted models & OpenAI. Code is Clean'N'Hackable. https://github.com/freckletonj/llmpal 4 comments emacs