--- title: "#local-llm articles | Hashnode" description: "Explore 135 articles tagged #local-llm on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/local-llm" --- Tag # #local-llm 135 posts · 0 followers [Dragos Roua](https://hashnode.com/@dragosroua) · [2d ago](https://hashnode.com/posts/video-running-nanbeige-4-2-3b-on-my-16gb-macbook-pro/6af2bf34cc1e239b8e7cee78) ### [\[ Video \] Running Nanbeige 4.2 3B on my 16GB MacBook Pro](https://dragosroua.hashnode.dev/video-running-nanbeige-4-2-3b-on-my-16gb-macbook-pro?utm_source=hashnode&utm_medium=feed) I tested Nanbeige 4.2 3b on a 16GB MacBook Pro. The 4bit quant is good, but the generation is relatively slow 2 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/video-running-nanbeige-4-2-3b-on-my-16gb-macbook-pro?utm_source=hashnode&utm_medium=feed) [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) [Charles Smith](https://hashnode.com/@smith8ca) · [3d ago](https://hashnode.com/posts/homelab-ai-stack/6af0d5c180c985a8be1119b3) ### [The 2026 Homelab AI Stack: What's Worth Running](https://chuckworks.hashnode.dev/homelab-ai-stack?utm_source=hashnode&utm_medium=feed) Hugging Face's advice after its July breach was to have a capable model on your own infrastructure before you need it. A homelab is a cheap place to learn what "capable" means. 6 min read · [chuckworks.hashnode.dev](https://chuckworks.hashnode.dev/homelab-ai-stack?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/homelab-ai-stack/6af0d5c180c985a8be1119b3) [Dragos Roua](https://hashnode.com/@dragosroua) · [4d ago](https://hashnode.com/posts/video-running-k2-horizon-3-7b-on-my-16gb-macbook-pro/6af076cbc8049b8101fee16f) ### [\[ Video \] Running K2 Horizon 3.7B on my 16GB MacBook Pro](https://dragosroua.hashnode.dev/video-running-k2-horizon-3-7b-on-my-16gb-macbook-pro?utm_source=hashnode&utm_medium=feed) K2 Horizon 3.7B runs comfortably on a 16GB MacBook Pro. Worth noting that the 7B parameter version was better, but way too slow. 2 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/video-running-k2-horizon-3-7b-on-my-16gb-macbook-pro?utm_source=hashnode&utm_medium=feed) [Dragos Roua](https://hashnode.com/@dragosroua) · [6d ago](https://hashnode.com/posts/can-ai-improve-itself-without-training-well-maybe/6aec8ad84c755372f06d7f0c) ### [Can AI Improve Itself Without Training? Well, Maybe…](https://dragosroua.hashnode.dev/can-ai-improve-itself-without-training-well-maybe?utm_source=hashnode&utm_medium=feed) A frontier model was capable to change a smaller model by just editing their weights. The short and long term consequences are fascinating. 3 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/can-ai-improve-itself-without-training-well-maybe?utm_source=hashnode&utm_medium=feed) [Avneesh Jadhav](https://hashnode.com/@avneeshjadhav) · [Nov 4](https://hashnode.com/posts/self-hosting-qwen-3-8-27b/6aeb33a7f824903c7be5643a) ### [Self-hosting Qwen 3.8 27B](https://avneeshjadhav.hashnode.dev/self-hosting-qwen-3-8-27b?utm_source=hashnode&utm_medium=feed) Self-hosted Qwen 3.8 27B on a GPU pod with 2x Nvidia RTX 3090 GPUs and vLLM. 1 min read · [avneeshjadhav.hashnode.dev](https://avneeshjadhav.hashnode.dev/self-hosting-qwen-3-8-27b?utm_source=hashnode&utm_medium=feed) [Dragos Roua](https://hashnode.com/@dragosroua) · [Nov 2](https://hashnode.com/posts/video-testing-ling-3-0-tiny-on-my-16gb-macbook-pro/6ae8507ca01cc82951721dc3) ### [\[ Video \] Testing Ling 3.0 Tiny on my 16GB MacBook Pro](https://dragosroua.hashnode.dev/video-testing-ling-3-0-tiny-on-my-16gb-macbook-pro?utm_source=hashnode&utm_medium=feed) Ling 3.0 Tiny is a surprisingly good model to run on a 16GB MacBook Pro. Test generation can go as fast as 45 tokens / second. 2 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/video-testing-ling-3-0-tiny-on-my-16gb-macbook-pro?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) [Dragos Roua](https://hashnode.com/@dragosroua) · [Oct 29](https://hashnode.com/posts/video-testing-spark-x2-6-4b-on-my-16gb-macbookpro/6ae30616bbb7f8db51bb1e7c) ### [\[ Video \] Testing Spark-X2.6–4B on my 16GB MacBookPro](https://dragosroua.hashnode.dev/video-testing-spark-x2-6-4b-on-my-16gb-macbookpro?utm_source=hashnode&utm_medium=feed) Spark 2.6 4B from Spark LLM is a decent model for its size. In my testing, there was even room left for other apps on my MacBook Pro 2 min read · [dragosroua.hashnode.dev](https://dragosroua.hashnode.dev/video-testing-spark-x2-6-4b-on-my-16gb-macbookpro?utm_source=hashnode&utm_medium=feed) [aiFetchly](https://hashnode.com/@aifetchly) · [Oct 28](https://hashnode.com/posts/inside-custom-ai-providers-multi-model-routing-in-aifetchly/6ae21446fe00fecb9d4acb3c) ### [Inside Custom AI Providers: Multi-Model Routing in aiFetchly](https://aifetchly-app.hashnode.dev/inside-custom-ai-providers-multi-model-routing-in-aifetchly?utm_source=hashnode&utm_medium=feed) Direct Answer: Power users optimize LLM latency, reasoning quality, and API expenses by configuring aiFetchly's Custom AI Provider engine to route distinct tasks across local and cloud models. By supp 3 min read · [aifetchly-app.hashnode.dev](https://aifetchly-app.hashnode.dev/inside-custom-ai-providers-multi-model-routing-in-aifetchly?utm_source=hashnode&utm_medium=feed)