News
Gemma 4 Fine-tuning Guide | Unsloth Documentation
6+ hour, 31+ min ago (717+ words) Train Gemma 4 by Google with Unsloth. You can now fine-tune Google's Gemma 4 E2B, E4B, 26B-A4B and 31B with Unslotharrow-up-right. Support includes all vision, text, audio and RL fine-tuning. Fine-tune Gemma 4 via our free Google Colab notebooks: If you want to preserve reasoning ability, you…...
Get started with Unsloth Studio | Unsloth Documentation
2+ week, 2+ day ago (324+ words) A guide for getting started with the fine-tuning studio, data recipes, model exporting, and chat. Unsloth Studio is a local, browser-based GUI for fine-tuning LLMs without writing any code. It wraps the training pipeline in a clean interface that handles…...
NVIDIA Nemotron 3 Nano - How To Run Guide | Unsloth Documentation
2+ week, 3+ day ago (702+ words) Run & fine-tune NVIDIA Nemotron 3 Nano locally on your device! NVIDIA releases Nemotron-3-Nano-4B, a 4B open hybrid MoE model that follows Nemotron-3-Super-120B-A12B and Nemotron-3-Nano-30B-A3B. The Nemotron family is designed for fast, accurate coding, math, and agentic workloads. They feature…...
Qwen3.5 Fine-tuning Guide | Unsloth Documentation
4+ week, 1+ day ago (624+ words) Learn how to fine-tune Qwen3.5 LLMs with Unsloth. You can now fine-tune Qwen3.5 model family (0.8B, 2B, 4B, 9B, 27B, 35B'A3B, 122B'A10B) with Unslotharrow-up-right. Support includes both vision and text fine-tuning. Qwen3.5'35B'A3B - bf16 LoRA works on 74GB VRAM. Unsloth makes Qwen3.5 train 1.5" faster and uses 50% less VRAM than FA2 setups. Qwen3.5 bf16 LoRA VRAM use: 0.8B: 3GB " 2B: 5GB " 4B: 10GB " 9B: 22GB " 27B: 56GB Fine-tune…...
GLM-5: How to Run Locally Guide | Unsloth Documentation
1+ mon, 2+ week ago (780+ words) Run the new GLM-5 model by Z.ai on your own local device! GLM-5 is Z.ai's latest reasoning model, delivering stronger coding, agent, and chat performance than GLM-4.7, and is designed for long context reasoning. It increases performance on benchmarks such…...
How to Fine-tune LLMs in VS Code with Unsloth | Unsloth Documentation
1+ mon, 2+ week ago (407+ words) Guide to fine-tuning models directly in Visual Studio Code via Unsloth and Google Colab. You can now fine-tune LLMs directly from Visual Studio Code (VSCode), locally or by using Google Colab's extension. In this guide, you'll learn how to connect…...
Qwen3-Coder-Next: How to Run Locally | Unsloth Documentation
1+ mon, 3+ week ago (966+ words) Guide to run Qwen3-Coder-Next locally on your device! Qwen releases Qwen3-Coder-Next, an 80B MoE model (3B active parameters) with 256K context for fast agentic coding and local use. It is comparable to the performance of models with 1020" more active parameters. The model excels…...
How to Run Local LLMs with Claude Code & OpenAI Codex | Unsloth Documentation
2+ mon, 4+ day ago (592+ words) Run Claude Code and OpenAI Codex on your local device guide. This step-by-step guide shows you how to connect open LLMs to Claude Code and Codex entirely locally, complete with screenshots. Run using any open model like DeepSeek, Qwen and…...
GLM-4.7-Flash: How To Run Locally | Unsloth Documentation
2+ mon, 1+ week ago (807+ words) Run & fine-tune GLM-4.7-Flash locally on your device! GLM-4.7-Flash is Z.ai's new 30B MoE reasoning model built for local deployment, delivering best-in-class performance for coding, agentic workflows, and chat. It uses ~3.6B parameters, supports 200K context, and leads SWE-Bench, GPQA, and reasoning…...
7x Longer Context Reinforcement Learning GRPO | Unsloth Documentation
2+ mon, 2+ week ago (911+ words) Learn how Unsloth enables ultra long context RL fine-tuning. Reinforcement learning's (RL) biggest challenge is supporting long reasoning traces. We're introducing new batching algorithms to enable ~7x longer context (can be more than 12x) RL training with no accuracy or speed degradation…...