home.social

#offline-ai — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #offline-ai, aggregated by home.social.

fetched live
  1. Как установить DeepSeek на ПК, чтобы пользоваться им без интернета

    Есть много причин, по которым вам может понадобиться установить нейросеть локально на компьютер. Например, вы не хотите зависеть от отключений интернета или вам нужно пользоваться ИИ на ноутбуке без сети. Так или иначе, такая опция предусмотрена и абсолютно легальна: DeepSeek распространяется бесплатно и у него открытый исходный код. Ниже я расскажу, как установить DeepSeek на компьютер при помощи приложения LM Studio.

    habr.com/ru/articles/1044886/

    #deepseek #eepseekr1 #llm #localllm #lmstudio #artificialintelligence #локальныемодели #offlineai #opensource #machinelearning

  2. Как установить DeepSeek на ПК, чтобы пользоваться им без интернета Есть много причин, по которым вам может понад...

    #deepseek #eepseek-r1 #llm #local-llm #lm-studio #artificial-intelligence #локальные-модели #offline-ai #open-source #machine-learning

    Origin | Interest | Match
  3. The Off-Switch You Do Not Own

    On 2 June 2026 Claude went down worldwide, taking the API, the Console, and Claude Code with it, and every business built on the model went down too. Centralised cloud intelligence carries an off-switch the operator does not hold, and the Mickai SIOS removes it by running the intelligence offline, sealed, on hardware you own.

    mickai.co.uk/articles/the-off-

    #sovereignai #aioutage #airesilience #offlineai #datasovereignty

  4. AI should feel like.

    Close.

    Private.

    Available.

    Useful without becoming another data pipeline.

    Your first local AI host does not have to be a giant machine.

    It can be your phone.

    #ai #privacy #offlineai #localai

    secretai.io/

  5. MakeUseOf: I built a private LLM on my home PC using a USB drive — it only knows what I put on it. “Building your own private, offline AI starts by downloading software that runs open-source language models directly on your computer’s processor. I like GPT4All because it has few requirements and gives you a desktop chat window that works without an internet connection. By using compressed […]

    https://rbfirehose.com/2026/05/31/makeuseof-i-built-a-private-llm-on-my-home-pc-using-a-usb-drive-it-only-knows-what-i-put-on-it/
  6. MakeUseOf: I built a private LLM on my home PC using a USB drive — it only knows what I put on it. “Building your own private, offline AI starts by downloading software that runs open-source language models directly on your computer’s processor. I like GPT4All because it has few requirements and gives you a desktop chat window that works without an internet connection. By using compressed […]

    https://rbfirehose.com/2026/05/31/makeuseof-i-built-a-private-llm-on-my-home-pc-using-a-usb-drive-it-only-knows-what-i-put-on-it/
  7. You can use Gemma 4, the newly released #ai model by #google fully #local on your device. This means that, after the download, you dont need internet to use the AI and conversations are not send to google, which is a huge #privacy win.
    You can download the model via the edge gallery app without login.

    Im not associated with google in any way.

    Do you use AI local on your device?

    #gemma4 #googleai #localai #offlineai #PrivacyWins #Ai #dataprivacy #DataProtection #privateai

  8. You can use Gemma 4, the newly released #ai model by #google fully #local on your device. This means that, after the download, you dont need internet to use the AI and conversations are not send to google, which is a huge #privacy win.
    You can download the model via the edge gallery app without login.

    Im not associated with google in any way.

    Do you use AI local on your device?

    #gemma4 #googleai #localai #offlineai #PrivacyWins #Ai #dataprivacy #DataProtection #privateai

  9. 🤔 Oh wow, a server that lets you hoard Wikipedia like a digital doomsday prepper! 🚀 Because clearly, what the world needs is more offline AI servers for when the internet apocalypse hits. 📚🔌 Let's just hope it's worth all those "free" hours fiddling with GitHub. Who needs the internet, anyway? 🌐🙄
    projectnomad.us #WikipediaHoarding #OfflineAI #DigitalDoomsdayPrepper #GitHubProjects #InternetApocalypse #HackerNews #ngated

  10. 🤔 Oh wow, a server that lets you hoard Wikipedia like a digital doomsday prepper! 🚀 Because clearly, what the world needs is more offline AI servers for when the internet apocalypse hits. 📚🔌 Let's just hope it's worth all those "free" hours fiddling with GitHub. Who needs the internet, anyway? 🌐🙄
    projectnomad.us #WikipediaHoarding #OfflineAI #DigitalDoomsdayPrepper #GitHubProjects #InternetApocalypse #HackerNews #ngated

  11. Milestone: 314 active voice rules! 🎙️

    SL5 Aura is our 100% offline, privacy-first voice control system. Instead of sending audio to the cloud, it processes commands locally using a hierarchical rule engine. Fast, secure, and customizable.

    Building a transparent tool for architects, not just another smart speaker. 🔧

    #OfflineAI #Privacy #VoiceControl #Linux #UnPlugTrump #SL5aura

  12. Lost in the woods? No signal? 😲
    Meet The Ark - an offline AI survival guide trained on real survival manuals.

    It works without internet and can tell you how to:
    • Find drinkable water 💧
    • Build shelter 🏕️
    • Treat injuries 🩹
    • Even survive a zombie apocalypse 🧟‍♂️

    Includes an accuracy meter ✅ so you know when a tip is 100% field-proven.
    Yes, this is real.

    apps.apple.com/us/app/survival

    #AI #Survival #OfflineAI #EmergencyPreparedness #Tech

  13. 🚀 New video on building an offline AI agent with Mistral 7B and a live SQL database.

    It can:
    Read schema
    Generate SQL
    Handle hallucinations
    Retry if it fails

    No internet, no APIs. Just real agentic logic.

    🎥 youtube.com/watch?v=xe9iDUi-0Y

    #AI #LLM #AgenticAI #OpenSource #OfflineAI

  14. 🚀 New video on building an offline AI agent with Mistral 7B and a live SQL database.

    It can:
    Read schema
    Generate SQL
    Handle hallucinations
    Retry if it fails

    No internet, no APIs. Just real agentic logic.

    🎥 youtube.com/watch?v=xe9iDUi-0Ys

  15. 🦙📡 New offline RAG tutorial just dropped!

    "Make Your Offline AI Model Talk to Local SQL DB"

    ➤ SentenceTransformer for embeddings
    ➤ FAISS for semantic search
    ➤ Local LLaMA (via llama.cpp) for generation
    ➤ SQL Server for storage

    🔐 Fully local & private — perfect for edge computing or secure AI workflows

    🎥 Video link: youtube.com/watch?v=3jFpLNglWB

    #FOSS #OfflineAI #LLaMA #RAG #LLM #AI

  16. 🦙📡 New offline RAG tutorial just dropped!

    "Make Your Offline AI Model Talk to Local SQL DB"

    ➤ SentenceTransformer for embeddings
    ➤ FAISS for semantic search
    ➤ Local LLaMA (via llama.cpp) for generation
    ➤ SQL Server for storage

    🔐 Fully local & private — perfect for edge computing or secure AI workflows

    🎥 Video link: youtube.com/watch?v=3jFpLNglWBc

  17. 🚀 Χρησιμοποιήστε AI τοπικά στο @ONLYOFFICE με τo Ollama! 🤖🔒

    Αποκτήστε πρόσβαση σε ισχυρά μοντέλα AI χωρίς σύνδεση στο διαδίκτυο, διατηρώντας ταυτόχρονα την απόλυτη ιδιωτικότητα των εγγράφων σας! 📂🔐

    🔹 Χωρίς καθυστερήσεις δικτύου
    🔹 Πλήρης έλεγχος των δεδομένων σας
    🔹 Υποστήριξη για Llama, Mistral, DeepSeek & πολλά άλλα

    📖 Διαβάστε το ολοκληρωμένο guide εδώ: onlyoffice.com/blog/el/2025/06

  18. Teaching AI offline… one smoothie at a time 🤖🍓
    I made 3 quick videos to help you:
    1️⃣ Run AI models offline
    2️⃣ Train them
    3️⃣ Generate your own data
    Everything is open source 🍃👇
    📺 youtu.be/lc6lVCe0XHI
    📺 youtu.be/FQr7VrK5RRQ
    📺 youtu.be/YB9cVyjV9Bo
    📂 github.com/hassanhabib/AI.Llam
    #AI #LLM #OfflineAI #OpenSource

  19. Teaching AI offline… one smoothie at a time 🤖🍓
    I made 3 quick videos to help you:
    1️⃣ Run AI models offline
    2️⃣ Train them
    3️⃣ Generate your own data
    Everything is open source 🍃👇
    📺 youtu.be/lc6lVCe0XHI
    📺 youtu.be/FQr7VrK5RRQ
    📺 youtu.be/YB9cVyjV9Bo
    📂 github.com/hassanhabib/AI.Llam

  20. Run AI models on your phone—no internet needed! Google AI Edge Gallery lets you chat, analyze images, and generate code offline, powered by Hugging Face models. Privacy-focused and portable. #AIEdgeGallery #AI #OfflineAI #TechInnovation

    pupuweb.com/will-google-ai-edg

  21. Just trained my own language model offline.
    No cloud. No APIs. Fine-tuned it on my data, merged it, and ran it with llama.cpp.
    This is what real AI literacy looks like.

    Documentation:
    github.com/hassanhabib/AI.Llam

    Video:
    youtube.com/watch?v=FQr7VrK5RR

    #AI #LLM #LoRA #OfflineAI #TinyLlama

  22. Just trained my own language model offline.
    No cloud. No APIs. Fine-tuned it on my data, merged it, and ran it with llama.cpp.
    This is what real AI literacy looks like.

    Documentation:
    github.com/hassanhabib/AI.Llam

    Video:
    youtube.com/watch?v=FQr7VrK5RRQ

  23. Run AI completely offline with Llama-CLI and C#! 🚀
    No cloud. Full control.
    Watch the full guide here: youtube.com/watch?v=lc6lVCe0XH
    #AI #CSharp #OfflineAI #LlamaCpp

  24. Run AI completely offline with Llama-CLI and C#! 🚀
    No cloud. Full control.
    Watch the full guide here: youtube.com/watch?v=lc6lVCe0XHI

  25. Turvallisin tapa käyttää DeepSeek-tekoälyä on ajaa se omalla tietokoneella – ilman pilvipalvelua ja tietovuotoja. Videolla näytän, miten saat sen toimimaan ilmaisilla sovelluksilla. 👉 youtu.be/B2fzjtSrw-4

    Näin vältät tietojen lähettämisen Kiinaan. Tarvitset vain riittävän tehokkaan tietokoneen, jossa on tarpeeksi VRAM-muistia.

    #DeepSeek #tekoäly #AI #tietoturva #yksityisyys #offlineAI #paikallinentekoäly #VRAM #ilmainensovellus #pilvipalveluton #tietosuoja #AIasennus #tekoälykotona

  26. Turvallisin tapa käyttää DeepSeek-tekoälyä on ajaa se omalla tietokoneella – ilman pilvipalvelua ja tietovuotoja. Videolla näytän, miten saat sen toimimaan ilmaisilla sovelluksilla. 👉 youtu.be/B2fzjtSrw-4

    Näin vältät tietojen lähettämisen Kiinaan. Tarvitset vain riittävän tehokkaan tietokoneen, jossa on tarpeeksi VRAM-muistia.

    #DeepSeek #tekoäly #AI #tietoturva #yksityisyys #offlineAI #paikallinentekoäly #VRAM #ilmainensovellus #pilvipalveluton #tietosuoja #AIasennus #tekoälykotona

  27. Ever wondered how to build an offline, personal RAG chatbot? 💬 I just shared a guide on creating a simple, local-only solution using Bun, libSQL, LangChain.js, and Ollama. 💻✨

    🌐 While everyone’s out there using Python for this kind of thing, I tackled it in JavaScript/TypeScript! No cloud dependency or API keys—just your machine and local resources. Perfect for anyone who wants privacy and full control. 🛡️

    #RAG #AI #OfflineAI #LangChain #Ollama #JavaScript #Bun

    flori.dev/reads/offline-rag-wi