Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Qwen3.8 Fine-tuning Guide | Unsloth Documentation
5+ hour, 32+ min ago (507+ words) Learn how to fine-tune Qwen3.8-27B with Unsloth. Qwen3.8-27B can now be fine-tuned and trained with reinforcement learning (RL) via Unsloth. It is a dense 27B unified vision-language model with native text, image and video support, thinking controls and a 262K context window. Unsloth trains…...
How to Serve Local AI Models from Any Device on Your Network with Unsloth LAN Access | Unsloth Documentation
1+ day, 15+ hour ago (707+ words) You can run local AI models on any device in your home or office with LAN access using Unsloth. With this enabled, local models can be accessed from a phone, laptop, or another computer on the same Wi-Fi or wired…...
Unsloth Dynamic 3.0 GGUFs | Unsloth Documentation
6+ day, 4+ hour ago (1725+ words) Unsloth Dynamic v3.0 is the next iteration of our Dynamic quantization and a major improvement over Dynamic v2.0. Today, we’re releasing Qwen3.8-27B Dynamic v3.0 quants that deliver >10% top-1% better accuracy at the same size compared to every other provider. This is an update of…...
Qwen3.8 - How to Run Locally | Unsloth Documentation
1+ week, 6+ day ago (650+ words) Guide to running Qwen3.8 quants on your local setup. Qwen3.8 is Qwen's new family of models, including Qwen3.8-27B, Qwen3.8-2.4T-A95B and Qwen3.8-Max. Qwen3.8 has vision and thinking capabilities, a 256K context window (up to 1M tokens). Qwen3.8-27B the upcoming 27B parameter model will be released this Friday. Qwen3.8-2.4T-A95B is a 2.4T parameter…...
NVIDIA Nemotron 3.5 Lightning: How To Run Locally | Unsloth Documentation
1+ week, 6+ day ago (717+ words) NVIDIA Nemotron-3.5-Lightning-30B-A3B is an open 30B parameter, 3B active hybrid reasoning MoE model built for high-volume task execution in long-running agents. It is designed for frequent agent calls including tool use, output validation, result formatting and subagent delegation. The model runs…...
Run Coding Agents with Local LLMs using Unsloth Start | Unsloth Documentation
1+ week, 6+ day ago (555+ words) First, make sure you have Unsloth installed. Then open Unsloth, load a model, go to your project folder, and run the command in terminal: You can replace claude with any agent below: Unsloth uses temporary or session-scoped provider configuration. It…...
How to Run Image Diffusion Models with Unsloth | Unsloth Documentation
2+ week, 1+ day ago (903+ words) Generate and edit images locally with Images, no code required. Start with a prompt, or upload an image and describe what you want to change. Where supported, LoRAs and reference images give you more control over the result. Choose from…...
Muse Glimmer Fine-tuning Guide | Unsloth Documentation
2+ week, 1+ day ago (518+ words) Train Meta's Muse Glimmer 30B model with Unsloth. You can now fine-tune Meta’s Muse Glimmer-30B with Unsloth. Muse Glimmer is a 30B parameter multimodal agentic model optimized for local deployment. Muse Glimmer is a dense causal Transformer with a dedicated perception encoder,…...
Inkling - How to Run Locally | Unsloth Documentation
1+ mon, 1+ week ago (1140+ words) Learn how to run Thinking Machine Labs' Inkling multimodal model locally. Inkling by Thinking Machines Labs is a new 975B parameter (41B active) open model with up to a 1M context window. Licensed under Apache 2.0, Inkling accepts text, images, and audio and generates…...
GLM-5.2 - How to Run Locally | Unsloth Documentation
1+ mon, 1+ week ago (1297+ words) Run the new GLM-5.2 model by Z.ai on local hardware! Dynamic 1-bit reaches ~76.2% top-1 accuracy while being 86% smaller. Dynamic 2-bit reaches ~82% accuracy while being 84% smaller. This means the model is not 82% worse since it's 84% smaller - it rather is only ~18% less…...