Updates and recent posts about Unsloth..

Posts
Description

Activity

@adrian_schmidt started using tool AWS Lambda , 1 month, 3 weeks ago.

Activity

@adrian_schmidt started using tool Amazon Web Services , 1 month, 3 weeks ago.

Activity

@adrian_schmidt started using tool Amazon SES , 1 month, 3 weeks ago.

Activity

@adrian_schmidt started using tool Amazon S3 , 1 month, 3 weeks ago.

Story

@laura_garcia shared a post, 1 month, 3 weeks ago

Software Developer, RELIANOID

𝗕𝗲𝘁𝘁 𝗕𝗿𝗮𝘀𝗶𝗹 𝟮𝟬𝟮𝟲

📍 São Paulo, Brazil 📅 May 5–8, 2026 𝗥𝗘𝗟𝗜𝗔𝗡𝗢𝗜𝗗 is heading to 𝗕𝗲𝘁𝘁 𝗕𝗿𝗮𝘀𝗶𝗹 𝟮𝟬𝟮𝟲 — 𝘵𝘩𝘦 𝘭𝘢𝘳𝘨𝘦𝘴𝘵 𝘌𝘥𝘛𝘦𝘤𝘩 𝘦𝘷𝘦𝘯𝘵 𝘪𝘯 𝘓𝘢𝘵𝘪𝘯 𝘈𝘮𝘦𝘳𝘪𝘤𝘢. 🚀 46,000+ professionals 💡 270+ companies 🌍 One shared goal: transforming education Let’s talk about secure, scalable, and high-performance digital learning. 👉 See you at Expo Cen..

Link

@koukibadr shared a link, 1 month, 3 weeks ago

Mobile Developer, Nventive

LiveData vs StateFlow

LiveData and StateFlow both stream data reactively, but differ in two key ways:

Initialization — LiveData needs no initial value; StateFlow requires one.

Lifecycle — LiveData is lifecycle-aware by default; StateFlow is not, so you need to wrap it in repeatOnLifecycle to avoid memory leaks.

Story

@pramod_kumar_0820 shared a post, 1 month, 3 weeks ago

Software Engineer, Teknospire

How To Crack Senior Java Interviews (6–10 YOE) In 4 Weeks

#system-... #Intervi... #spring ... #java #Microse...

A practical 4-week roadmap to crack Senior Java Developer interviews (6–10 YOE), covering Core Java, Spring Boot internals, Microservices, System Design, and real-world interview strategies.

Senior Java Interviews (6–10 YOE) In 4 Weeks

Story WPWeb Infotech Team

@rafidbottler shared a post, 1 month, 3 weeks ago

Full Stack Engineer, WPWeb Infotech

Angular vs React: Which Framework Is Better for Web Development?

Angular vs React: discover the main differences, performance, and use cases to choose the best framework for modern web development projects in 2026.

Story

@viktoriiagolovtseva shared a post, 1 month, 3 weeks ago

How to Make Your Jira Sprint Planning Really Agile

You know the drill:build a product roadmap in Jira, create your product backlog, review it, update the user stories, come up with a sprint goal before the meeting, and finally, review every story to decide which ones need to be completed this sprint. Easier said than done, right? Well-planned sprint..

Story

@laura_garcia shared a post, 1 month, 3 weeks ago

Software Developer, RELIANOID

Not all 𝗱𝗶𝗴𝗶𝘁𝗮𝗹 𝗰𝗲𝗿𝘁𝗶𝗳𝗶𝗰𝗮𝘁𝗲𝘀 are created equal

🚨 Not all 𝗱𝗶𝗴𝗶𝘁𝗮𝗹 𝗰𝗲𝗿𝘁𝗶𝗳𝗶𝗰𝗮𝘁𝗲𝘀 are created equal. From 𝗗𝗩, 𝗢𝗩, 𝗘𝗩 𝘁𝗼 𝗺𝗧𝗟𝗦 𝗰𝗹𝗶𝗲𝗻𝘁 𝗰𝗲𝗿𝘁𝘀 and 𝗰𝗼𝗱𝗲 𝘀𝗶𝗴𝗻𝗶𝗻𝗴, each plays a different role in your security posture. 🔐 Encryption is just the beginning: → Identity validation → Trust chains (Root → Intermediate → Leaf) → Secure software delivery → Zero Trust..

Unsloth is an open-source toolkit for training and fine-tuning large language models faster and with less memory than a standard Hugging Face stack. Its core library replaces PyTorch's default autograd with custom backpropagation kernels written in OpenAI's Triton language, which is where most of its speed and memory savings come from. It supports LoRA, QLoRA, full fine-tuning, reinforcement learning, pretraining, and 4-bit, 16-bit, and FP8 training, across more than 500 text, vision, audio, and embedding models.

The practical draw is hardware reach. QLoRA workflows in Unsloth let you fine-tune an 8B model on a single 12 GB consumer GPU, and the project headlines roughly 2x faster training with about 70 percent less VRAM versus baseline implementations, though the exact figures vary by model, GPU, and config. A 2026 update added faster mixture-of-experts training, with models like Qwen3-30B-A3B fine-tunable on about 17.5 GB of VRAM. It runs on NVIDIA (including Blackwell and DGX Spark), AMD, and Intel GPUs, with free Colab and Kaggle notebooks for trying it without local hardware.

It fits cleanly into the local-AI workflow. Unsloth integrates with Hugging Face transformers and TRL, and uses llama.cpp to save and run models, exporting to GGUF for Ollama or LM Studio as well as safetensors. As of 2026 it also ships Unsloth Studio, a local no-code GUI that covers the full lifecycle from dataset creation to training to running and comparing GGUF and safetensors models, with tool-calling, web search, and an OpenAI-compatible API, all running offline on Mac and Windows, with the core library under the Apache 2.0 license.