--- title: "#llama articles | Hashnode" description: "Explore 168 articles tagged #llama on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/llama" --- Tag # #llama 168 posts · 39 followers [Muhammad Ariel Shakaramiro](https://hashnode.com/@arielshakaramiro) · [Sep 25](https://hashnode.com/posts/llama3-8b-qlora-finetuning-free-colab/6ab6811de566a637dd49dd06) ### [Fine-Tuning Llama 3.1 8B for Free on Colab: QLoRA, Unsloth, and a Compression Claim That Doesn't Hold Up](https://shaka-ai.hashnode.dev/llama3-8b-qlora-finetuning-free-colab?utm_source=hashnode&utm_medium=feed) How to fine-tune Llama 3.1 8B with QLoRA on free Colab, plus a real check of a 4-bit compression claim that turns out to be wrong. 7 min read · [shaka-ai.hashnode.dev](https://shaka-ai.hashnode.dev/llama3-8b-qlora-finetuning-free-colab?utm_source=hashnode&utm_medium=feed) [Muhammad Ariel Shakaramiro](https://hashnode.com/@arielshakaramiro) · [Sep 25](https://hashnode.com/posts/serving-llm-llamacpp-cache-wrong-answer-trap/6ab68b524750c7424a5bd7aa) ### [Serving Your Own Model with llama.cpp: GPU Offload, Caching, and the Trap of a Stuck Wrong Answer](https://shaka-ai.hashnode.dev/serving-llm-llamacpp-cache-wrong-answer-trap?utm_source=hashnode&utm_medium=feed) Serving a GGUF model with llama.cpp, caching answers in SQL, and a demo of why a cached wrong answer doesn't just go away on its own. 7 min read · [shaka-ai.hashnode.dev](https://shaka-ai.hashnode.dev/serving-llm-llamacpp-cache-wrong-answer-trap?utm_source=hashnode&utm_medium=feed) [Internals Decoded](https://hashnode.com/@internalsdecoded) · [Aug 31](https://hashnode.com/posts/open-vs-closed-models/6a95d73abab12d9afbc9463b) ### [Open vs Closed Models: What 'Open Source AI' Really Means](https://internals-decoded.hashnode.dev/open-vs-closed-models?utm_source=hashnode&utm_medium=feed) Weights, data, licenses: the three things people conflate when they say open source. 11 min read · [internals-decoded.hashnode.dev](https://internals-decoded.hashnode.dev/open-vs-closed-models?utm_source=hashnode&utm_medium=feed) [Rahul Sai Indeevar V](https://hashnode.com/@rahul-ai) · [Aug 28](https://hashnode.com/posts/understanding-lora-parameter-efficient-fine-tuning-for-modern-llms/6a912f5aed98e5cc0cf60b6f) ### [Understanding LoRA: Parameter-Efficient Fine-Tuning for Modern LLMs](https://rahul-ai.hashnode.dev/understanding-lora-parameter-efficient-fine-tuning-for-modern-llms?utm_source=hashnode&utm_medium=feed) Large Language Models (LLMs) and foundation models like LLaMA, GPT, and ViTs have billions of parameters. As these models scale, traditional full fine-tuning—updating every weight in the network—becom 9 min read · [rahul-ai.hashnode.dev](https://rahul-ai.hashnode.dev/understanding-lora-parameter-efficient-fine-tuning-for-modern-llms?utm_source=hashnode&utm_medium=feed) [Manu Shukla](https://hashnode.com/@mr-manushukla) · [Jul 30](https://hashnode.com/posts/meta-shut-down-its-llama-api-in-2026-migrate-your-app-and-compare-host-costs/6a6bd86e7e4cadd4955563bd) ### [Meta shut down its Llama API in 2026: migrate your app and compare host costs](https://ecorpit.hashnode.dev/meta-shut-down-its-llama-api-in-2026-migrate-your-app-and-compare-host-costs?utm_source=hashnode&utm_medium=feed) Meta shut down its Llama API in 2026: migrate your app and compare host costs Summary. Meta shut down its hosted Llama API on 6 July 2026, and requests to the old endpoint now return a sunset response 14 min read · [ecorpit.hashnode.dev](https://ecorpit.hashnode.dev/meta-shut-down-its-llama-api-in-2026-migrate-your-app-and-compare-host-costs?utm_source=hashnode&utm_medium=feed) [Sameer Selokar](https://hashnode.com/@sameers9823) · [Jul 5](https://hashnode.com/posts/prompt-engineering-zero-shot-few-shot-chain-of-thought-prompting/6a4a9eca60779baaf0d9b9d8) ### [Prompt Engineering : Zero-Shot, Few-Shot & Chain of Thought Prompting](https://blogbysameer.hashnode.dev/prompt-engineering-zero-shot-few-shot-chain-of-thought-prompting?utm_source=hashnode&utm_medium=feed) Master Prompt Engineering with real JavaScript examples of Zero-Shot, Few-Shot, and Chain of Thought prompting for LLMs. 5 min read · [blogbysameer.hashnode.dev](https://blogbysameer.hashnode.dev/prompt-engineering-zero-shot-few-shot-chain-of-thought-prompting?utm_source=hashnode&utm_medium=feed) [Hưng Phát Laptop](https://hashnode.com/@hungphatlaptopnews) · [Jun 19](https://hashnode.com/posts/phn-tch-k-thut-laptop-15-triu-cho-aiml-developer/6a34c3d2a39ed8c6dff7c84b) ### [Phân tích kỹ thuật Laptop <15 triệu cho AI/ML Developer](https://hungphatlaptopnews.hashnode.dev/phn-tch-k-thut-laptop-15-triu-cho-aiml-developer?utm_source=hashnode&utm_medium=feed) Đối với một AI/ML Developer, chiếc laptop không chỉ là công cụ soạn thảo code mà còn là môi trường thực thi mô hình. Với ngân sách dưới 15 triệu đồng, việc lựa chọn phần cứng đòi hỏi sự cân nhắc kỹ lư 3 min read · [hungphatlaptopnews.hashnode.dev](https://hungphatlaptopnews.hashnode.dev/phn-tch-k-thut-laptop-15-triu-cho-aiml-developer?utm_source=hashnode&utm_medium=feed) [Hưng Phát Laptop](https://hashnode.com/@hungphatlaptopnews) · [Jun 14](https://hashnode.com/posts/phn-tch-cu-hnh-laptop-cho-aiml-developer-ng-ch-nhn-vo-cpu/6a2e43f901df57d7884e719a) ### [Phân tích cấu hình Laptop cho AI/ML Developer: Đừng chỉ nhìn vào CPU](https://hungphatlaptopnews.hashnode.dev/phn-tch-cu-hnh-laptop-cho-aiml-developer-ng-ch-nhn-vo-cpu?utm_source=hashnode&utm_medium=feed) Đối với một AI/ML Developer, việc chọn mua laptop không đơn thuần là chọn một thiết bị làm việc văn phòng. Bài viết Lần đầu mua Laptop: 10 điều phải biết trước khi ra Cửa hàng nhấn mạnh việc xác định 3 min read · [hungphatlaptopnews.hashnode.dev](https://hungphatlaptopnews.hashnode.dev/phn-tch-cu-hnh-laptop-cho-aiml-developer-ng-ch-nhn-vo-cpu?utm_source=hashnode&utm_medium=feed) [Hưng Phát Laptop](https://hashnode.com/@hungphatlaptopnews) · [Jun 12](https://hashnode.com/posts/laptop-vn-phng-2026-la-chn-thc-t-cho-aiml-developer-mqbadqlt/6a2c561311b69e390cd33f45) ### [Laptop văn phòng 2026: Lựa chọn thực tế cho AI/ML Developer?](https://hungphatlaptopnews.hashnode.dev/laptop-vn-phng-2026-la-chn-thc-t-cho-aiml-developer-mqbadqlt?utm_source=hashnode&utm_medium=feed) Khi nhìn vào danh sách các dòng laptop văn phòng phổ biến năm 2026, một câu hỏi đặt ra cho cộng đồng developer: Liệu những thiết bị này có đủ sức gánh vác các workload AI/ML ngày càng nặng nề, hay chú 3 min read · [hungphatlaptopnews.hashnode.dev](https://hungphatlaptopnews.hashnode.dev/laptop-vn-phng-2026-la-chn-thc-t-cho-aiml-developer-mqbadqlt?utm_source=hashnode&utm_medium=feed) [Yaroslav Pristupa](https://hashnode.com/@yarodev) · [Jun 8](https://hashnode.com/posts/step-by-step-guide-to-running-gemma-4-26b-locally-on-budget-gpus/6a26faa236de4d4818e4dacb) ### [Step-by-step guide to running Gemma-4 26B locally on budget GPUs](https://code-friendly.hashnode.dev/step-by-step-guide-to-running-gemma-4-26b-locally-on-budget-gpus?utm_source=hashnode&utm_medium=feed) How to run a 26-billion parameter AI model on a standard developer laptop with an 8GB GPU, using llama.cpp. 12 min read · [code-friendly.hashnode.dev](https://code-friendly.hashnode.dev/step-by-step-guide-to-running-gemma-4-26b-locally-on-budget-gpus?utm_source=hashnode&utm_medium=feed)