home.social

#offlinellm — Public Fediverse posts

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

fetched live
  1. Benchmarked Nanbeige 4.2 3B (BF16) as a browser-agent planner. Surprisingly strong for its size — competitive with much larger open-weight models on WebBrain.

    www.webbrain.one/blog/nanbeige-42-3b-bf16-planner-benchmark

    #offlinellm #nanbeige

  2. Benchmarked Nanbeige 4.2 3B (BF16) as a browser-agent planner. Surprisingly strong for its size — competitive with much larger open-weight models on WebBrain.

    www.webbrain.one/blog/nanbeige-42-3b-bf16-planner-benchmark

    #offlinellm #nanbeige

  3. Benchmarked Poolside's new Laguna S 2.1 (118B-A8B) as a browser-agent planner. 71% Sonnet alignment. Near Hy3/MiniMax M3 but below them, and below Gemma 4 31B QAT / Qwen 3.6 27B (~77%).

    Best US open-weight in its class, half the size of M3 👇

    webbrain.one/blog/poolside-lag

    #offlinellm #poolside #llm #ai #opensource #qwen #gemma #benchmark #llama #llamacpp #ollama

  4. Benchmarked Poolside's new Laguna S 2.1 (118B-A8B) as a browser-agent planner. 71% Sonnet alignment. Near Hy3/MiniMax M3 but below them, and below Gemma 4 31B QAT / Qwen 3.6 27B (~77%).

    Best US open-weight in its class, half the size of M3 👇

    webbrain.one/blog/poolside-lag

    #offlinellm #poolside #llm #ai #opensource #qwen #gemma #benchmark #llama #llamacpp #ollama

  5. Have you heard about #ensu by #ente? It's a fully local / offline AI assistant that works decently well for simple queries. I'm actually quite excited. You just need to remember that it's a very 1st version so not everything works as it should. As far as I can tell, the model they're using is Llama 3 (1.2 GB). Depending on your hardware it will run smoothly... or not 😁

    ente.com/ensu

    #localAI #offlineLLM

  6. Have you heard about #ensu by #ente? It's a fully local / offline AI assistant that works decently well for simple queries. I'm actually quite excited. You just need to remember that it's a very 1st version so not everything works as it should. As far as I can tell, the model they're using is Llama 3 (1.2 GB). Depending on your hardware it will run smoothly... or not 😁

    ente.com/ensu

    #localAI #offlineLLM

  7. 🚀 Turn your offline LLM into a REST API with ASP.NET Core.
    💬 Call it from anywhere.
    🔒 100% private.
    🎥 Tutorial → youtube.com/watch?v=PtkYhjIma1Q
    #AI #OfflineLLM #DotNet #RESTAPI

  8. 🚀 Turn your offline LLM into a REST API with ASP.NET Core.
    💬 Call it from anywhere.
    🔒 100% private.
    🎥 Tutorial → youtube.com/watch?v=PtkYhjIma1Q