LocalAI_API's profile picture. OpenAI Open Source alternative. LocalAI is a community, drop-in replacement API compatible with OpenAI for local CPU/GPU inferencing

LocalAI

@LocalAI_API

OpenAI Open Source alternative. LocalAI is a community, drop-in replacement API compatible with OpenAI for local CPU/GPU inferencing

Disematkan

👋LocalAI 3.7.0 is here! This is one of our coolest release yet. We've just shipped full Agentic MCP Support in the API, turning LocalAI into a platform for building local-first AI agents that use real tools. And it's all integrated also in the WebUI. 🤖 (Thread 👇)


LocalAI memposting ulang

btw. not sure if I mentioned it, I created github.com/a-i-a-d/Tankie It's currently just using LocalAGI actions through simple tcp and a wrapper, but works for letting an LLM drive. Just busy with other stuff, however hackweek is coming up, so hope to get more done there.


We are Trending on Github ! Thank you for your support 🫶

@LocalAI_API is trending now on Github! Thank you everyone for your support! Let's go and democratize AI and Agentic software!

mudler_it's tweet image. @LocalAI_API is trending now on Github!

Thank you everyone for your support! Let's go and democratize AI and Agentic software!


🚨 New model alert! 🚨 We've added YanoljaNEXT-Rosetta-27B-2511, a multilingual translation model built on Gemma3, to LocalAI! 🚀 Try it out: `local-ai run yanoljanext-rosetta-27b-2511` #LocalAI #AI #NewModel #Translation


🎉 New model alert! 🎉 We've added nvidia.qwen3-nemotron-32b-rlbff – a powerful 32B Qwen3 model fine-tuned for top-notch reasoning & generation. 🤯 Try it out in LocalAI with: `local-ai run nvidia.qwen3-nemotron-32b-rlbff` 🚀 #LocalAI #LLM #Qwen3


🚨 New model alert! 🚨 GroveMoE-Base is here! 🎉 A super efficient 33B MoE LLM, great for speed & resource-constrained environments. Get it running locally with: `local-ai run grovemoe-base-i1` 🚀 #LocalAI #LLM #NewModel


🔥 New models just dropped in LocalAI! 🔥 Check out Qwen3-VL-2B, ReForm-32B, Qwen3-4B-Thinking, and Qwen3-Yoyo-V4-42B! 🤯 Get them running locally with: `local-ai run model_name_here` 😉


🚨 New model alert! 🚨 Just added Qwen3-4B-Thinking-2507-GSPO-Easy to the gallery – a 4B model fine-tuned for step-by-step reasoning & problem-solving! 🧠 Try it out in LocalAI with: `local-ai run Qwen3-4B-Thinking-2507-GSPO-Easy.Q4_K_M.gguf` #LocalAI #LLM #NewModel


🤯 New model alert! ReForm-32B is here – a beast for math problems & formal proofs! 🤯 Try it out in LocalAI with: `local-ai run ReForm-32B.i1-Q4_K_M.gguf` 🚀 #LocalAI #LLM #AI #Math


🚨 New model alert! 🚨 We've got **Qwen3-VL-30B-A3B-Instruct** in the gallery now! 🎉 This multimodal beast is packed with vision-language capabilities. 🤯 Try it out with: `local-ai run qwen3-vl-30b-a3b-instruct` 🚀 #LocalAI #Qwen3 #Multimodal #AI


🚨 New model alert! 🚨 Meet Qwen3-Grand-Horror-Light-1.7B – a 1.7B horror storytelling model! 👻 Perfect for spooky roleplay & creative writing. Get it running in LocalAI with: `local-ai run qwen3-grand-horror-light-1.7b` #LocalAI #LLM #AI #Horror


🚨 New model alert! 🚨 Just added financial-gpt-oss-20b! 💰 A 20B MoE model fine-tuned for financial analysis - stocks, trading signals & more. 📈 Try it out in LocalAI with: `local-ai run financial-gpt-oss-20b-q8` #LocalAI #LLM #Finance #NewModel


🚨 New model alert! 🚨 We've got Qwen3-Nemotron-32B-RLBFF in the house – a powerful 32B RLBFF model from NVIDIA! 🤯 Ready to give it a spin? Just run: `local-ai run qwen3-nemotron-32b-rlbff-i1` 🚀 #LocalAI #LLM #Qwen3


Loading...

Something went wrong.


Something went wrong.