--- title: "#local-ai articles | Hashnode" description: "Explore 101 articles tagged #local-ai on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/local-ai" --- Tag # #local-ai 101 posts · 0 followers [Robert Degallan](https://hashnode.com/@robertdegallan) · [2d ago](https://hashnode.com/posts/alibaba-and-unknown-european-it-company-are-cooking-something-that-could-crush-ai-goliaths/6af1ef70e8f6898121488da1) ### [Alibaba + unknown European IT company are cooking something that could crush AI Goliaths](https://robertdegallan.hashnode.dev/alibaba-and-unknown-european-it-company-are-cooking-something-that-could-crush-ai-goliaths?utm_source=hashnode&utm_medium=feed) Alibaba's Qwen4-27B model (David) and Amadeus' CoDoc (the rock) standard could tremble the AI Goliaths by providing a small local brain with context. 3 min read · [robertdegallan.hashnode.dev](https://robertdegallan.hashnode.dev/alibaba-and-unknown-european-it-company-are-cooking-something-that-could-crush-ai-goliaths?utm_source=hashnode&utm_medium=feed) [Dragos Roua](https://hashnode.com/@dragosroua) · [Nov 4](https://hashnode.com/posts/running-a-billion-parameter-model-lfm3-1-7b-on-a-raspberry-pi/6aeb5f5bc70a133bf2cb160d) ### [Running A Billion Parameter Model (LFM3 1.7B) on a Raspberry Pi](https://dragosroua.hashnode.dev/running-a-billion-parameter-model-lfm3-1-7b-on-a-raspberry-pi?utm_source=hashnode&utm_medium=feed) A Raspberry Pi 4 can run comfortably (3t/s) LFM3 1.7B. Not usable for heavy coding, but good enough for an orchestrator. 3 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/running-a-billion-parameter-model-lfm3-1-7b-on-a-raspberry-pi?utm_source=hashnode&utm_medium=feed) [2](https://hashnode.com/posts/running-a-billion-parameter-model-lfm3-1-7b-on-a-raspberry-pi/6aeb5f5bc70a133bf2cb160d) [Dragos Roua](https://hashnode.com/@dragosroua) · [Nov 3](https://hashnode.com/posts/an-ai-model-in-your-browser-lfm3-omni-2-2b-on-a-16gb-mbp/6ae9db1c1898719da94d7e15) ### [An AI Model in your Browser? LFM3 Omni 2.2B on a 16GB MBP](https://dragosroua.hashnode.dev/an-ai-model-in-your-browser-lfm3-omni-2-2b-on-a-16gb-mbp?utm_source=hashnode&utm_medium=feed) I tested Liquid Foundation LFM3 Omni 2.2B model, in a browser on my MacBook Pro. At 1.6GB download, the experience is spectacular. 2 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/an-ai-model-in-your-browser-lfm3-omni-2-2b-on-a-16gb-mbp?utm_source=hashnode&utm_medium=feed) [Dragos Roua](https://hashnode.com/@dragosroua) · [Oct 31](https://hashnode.com/posts/video-testing-apple-intelligence-on-my-16gb-macbook-pro/6ae5997ad60b1eeba21d2978) ### [\[ Video \] Testing Apple Intelligence on my 16GB MacBook Pro](https://dragosroua.hashnode.dev/video-testing-apple-intelligence-on-my-16gb-macbook-pro?utm_source=hashnode&utm_medium=feed) I tested the Apple Intelligence model Apple ships with its default install, by actually chatting with it. One of the fastest models so far. 2 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/video-testing-apple-intelligence-on-my-16gb-macbook-pro?utm_source=hashnode&utm_medium=feed) [Quentin Merle](https://hashnode.com/@quentinmerle) · [Oct 28](https://hashnode.com/posts/implementing-client-side-ai-in-e-commerce-webllm-privacy-first-architecture/6ae20e4b1af7a5664068260d) ### [Implementing Client-Side AI in E-Commerce (WebLLM & Privacy-First Architecture)](https://vibrisse-studio.hashnode.dev/implementing-client-side-ai-in-e-commerce-webllm-privacy-first-architecture?utm_source=hashnode&utm_medium=feed) How to bring Enterprise-grade conversational AI to e-commerce without the six-figure cloud infrastructure costs. A deep dive into Edge AI, WebGPU, and deterministic JavaScript guardrails using Llama 3.2 and native browser APIs. 9 min read · [vibrisse-studio.hashnode.dev](https://vibrisse-studio.hashnode.dev/implementing-client-side-ai-in-e-commerce-webllm-privacy-first-architecture?utm_source=hashnode&utm_medium=feed) [Adi Shik](https://hashnode.com/@adishik) · [Oct 25](https://hashnode.com/posts/tensward-benchmarks/6addd87f018bf08f1a7a03c6) ### [What a 1997 chess engine taught me about LLM inference](https://openingthehood.hashnode.dev/tensward-benchmarks?utm_source=hashnode&utm_medium=feed) TL;DR You don't need an LLM agent to optimize inference. Across six tuning tracks on an NVIDIA L4, Tensward's expert rules and heuristics matched frontier LLM agents running at maximum effort - Astra 10 min read · [openingthehood.hashnode.dev](https://openingthehood.hashnode.dev/tensward-benchmarks?utm_source=hashnode&utm_medium=feed) [Haithem Slimi](https://hashnode.com/@haithem-slimi) · [Oct 14](https://hashnode.com/posts/the-memory-wall-how-nvidia-s-rtx-spark-changes-the-ai-bottleneck/6acffbafb459ea580cb3fa7e) ### [The Memory Wall: How NVIDIA’s RTX Spark Changes the AI Bottleneck](https://nightthoughts.me/the-memory-wall-how-nvidia-s-rtx-spark-changes-the-ai-bottleneck?utm_source=hashnode&utm_medium=feed) Why AI workloads are memory-bound, and how NVIDIA RTX Spark's unified memory changes local inference, RAG and fine-tuning on a desktop. 13 min read · [nightthoughts.me](https://nightthoughts.me/the-memory-wall-how-nvidia-s-rtx-spark-changes-the-ai-bottleneck?utm_source=hashnode&utm_medium=feed) [2](https://hashnode.com/posts/the-memory-wall-how-nvidia-s-rtx-spark-changes-the-ai-bottleneck/6acffbafb459ea580cb3fa7e) [Sanjay Jana](https://hashnode.com/@sjana7797) · [Oct 11](https://hashnode.com/posts/building-solomon-a-private-local-first-ai-assistant/6acb63aa96cee34a2028101c) ### [Building Solomon: a private, local-first AI assistant](https://codedecoder.hashnode.dev/building-solomon-a-private-local-first-ai-assistant?utm_source=hashnode&utm_medium=feed) Why we built Solomon Solomon is an AI assistant that chats, searches the web with citations, reads your files and draws images, and most of it runs on our own machines. We built it to see how far a pr 5 min read · [codedecoder.hashnode.dev](https://codedecoder.hashnode.dev/building-solomon-a-private-local-first-ai-assistant?utm_source=hashnode&utm_medium=feed) [Haithem Slimi](https://hashnode.com/@haithem-slimi) · [Oct 9](https://hashnode.com/posts/running-llms-locally-how-to-pick-the-right-tool-and-model-for-your-machine/6ac87f7024f10ae309d2d4d6) ### [Running LLMs Locally: How to Pick the Right Tool and Model for Your Machine](https://nightthoughts.me/running-llms-locally-how-to-pick-the-right-tool-and-model-for-your-machine?utm_source=hashnode&utm_medium=feed) A practical guide for getting your first local model running — and choosing one that actually fits the hardware you already own. 17 min read · [nightthoughts.me](https://nightthoughts.me/running-llms-locally-how-to-pick-the-right-tool-and-model-for-your-machine?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/running-llms-locally-how-to-pick-the-right-tool-and-model-for-your-machine/6ac87f7024f10ae309d2d4d6) [Haithem Slimi](https://hashnode.com/@haithem-slimi) · [Oct 8](https://hashnode.com/posts/samsung-s-littlebit-makes-giant-ai-models-fit-on-your-laptop/6ac78adaf31a506f107c67c7) ### [Samsung's LittleBit Makes Giant AI Models Fit on Your Laptop](https://nightthoughts.me/samsung-s-littlebit-makes-giant-ai-models-fit-on-your-laptop?utm_source=hashnode&utm_medium=feed) Samsung Research's peer-reviewed LittleBit method compresses large language models enough to run locally. How it works and what it changes. 4 min read · [nightthoughts.me](https://nightthoughts.me/samsung-s-littlebit-makes-giant-ai-models-fit-on-your-laptop?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/samsung-s-littlebit-makes-giant-ai-models-fit-on-your-laptop/6ac78adaf31a506f107c67c7)