{"slug": "unsloth-easily-run-and-train-models-locally", "title": "Unsloth: Easily run and train models locally", "summary": "Unsloth launched Unsloth Studio, a desktop application for Mac and Windows that runs AI models offline, supporting GGUF and Safetensors formats with tool-calling, web search, and an OpenAI-compatible API. The tool enables side-by-side model comparison, dataset creation from documents, and optimized training for over 500 models, while also offering a free open-source version for fine-tuning on NVIDIA GPUs via Google Colab or Kaggle.", "body_md": "Unsloth Studio runs 100% offline on your **Mac** and **Windows** device. Run GGUF and Safetensors models with tool-calling, web search, and OpenAI compatible API.\n\nCompare models side by side and upload images, docs, audio, code files and more.\n\nAuto-create datasets from PDF, CSV, JSON docs and start training with real-time observability.\n\nUnsloth's custom kernels supports optimized training for LoRA, FP8, FFT, PT and 500+ models including text, vision, audio and embeddings.\n\nChat with and compare 2 different models, such as a base model and a fine-tuned one, to see how their outputs differ.\n\nJust load your first GGUF/model, then the second, and voilà!\n\nData Recipes transforms your docs into useable datasets via graph-node workflow. Upload unstructured or structured files like PDFs, CSV and JSON. Unsloth Data Recipes auto turns documents into your desired formats.\n\nExport any model, including your fine-tuned models, to safetensors, or GGUF for use with llama.cpp, vLLM, Ollama, and more.\n\nWhy not try our fully free open source version? Finetune 2X faster on a single NVIDIA GPU for free on Google Colab or Kaggle Notebooks.", "url": "https://wpnews.pro/news/unsloth-easily-run-and-train-models-locally", "canonical_source": "https://unsloth.ai/", "published_at": "2026-06-18 23:15:29+00:00", "updated_at": "2026-06-18 23:30:52.515667+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-tools", "ai-infrastructure", "developer-tools"], "entities": ["Unsloth", "Unsloth Studio", "GGUF", "Safetensors", "OpenAI", "NVIDIA", "Google Colab", "Kaggle"], "alternates": {"html": "https://wpnews.pro/news/unsloth-easily-run-and-train-models-locally", "markdown": "https://wpnews.pro/news/unsloth-easily-run-and-train-models-locally.md", "text": "https://wpnews.pro/news/unsloth-easily-run-and-train-models-locally.txt", "jsonld": "https://wpnews.pro/news/unsloth-easily-run-and-train-models-locally.jsonld"}}