News
Diffusion Gemma - How to Run Locally | Unsloth Documentation
3+ hour, 26+ min ago (1057+ words) Diffusion Gemma 26 B-A4 B is Google Deep Mind's new open multimodal model, built on the Gemma 4 Mo E architecture. With support for 256 K context, 140+ languages, Diffusion Gemma is designed for high-speed text generation across text, video and image inputs. Diffusion Gemma…...
Unsloth Joins the Py Torch Ecosystem
4+ week, 2+ day ago (20+ words) Unsloth May 11, 2026 " By Daniel & Michael Run + train models via a UI...
Mistral 3. 5 - How To Run Locally | Unsloth Documentation
1+ mon, 1+ week ago (604+ words) Guide for Mistral Mistral 3. 5 models, to run or fine-tune locally on your device Mistral releases Mistral-Medium-3. 5-128 B, their new dense 128 B parameter, multimodal, hybrid reasoning model. It supports text and image input, text output, a 256 K context window and excels…...
Mini Max-M2. 7 - How to Run Locally | Unsloth Documentation
1+ mon, 4+ week ago (769+ words) Run Mini Max-M2. 7 LLM locally on your own device! Mini Max-M2. 7 is a new open model for agentic coding and chat use-cases. The model achieves SOTA performance in SWE-Pro (56. 22%) and Terminal Bench 2 (57. 0%). The 230 B parameters (10 B active) model has a…...
GLM-5: How to Run Locally Guide | Unsloth Documentation
2+ mon, 3+ day ago (742+ 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…...
GLM-5. 1 - How to Run Locally | Unsloth Documentation
2+ mon, 3+ day ago (844+ words) Run the new GLM-5. 1 model by Z. ai on your own local device! GLM-5. 1 is Z. ai's new open model. Compared with GLM-5, it delivers major improvements in coding, agentic tool use, reasoning, role-play, long-horizon agentic tasks, and overall chat quality. The…...
Gemma 4 Fine-tuning Guide | Unsloth Documentation
2+ mon, 1+ week ago (717+ words) Train Gemma 4 by Google with Unsloth. You can now fine-tune Google's Gemma 4 E2 B, E4 B, 26 B-A4 B and 31 B 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…...
Get started with Unsloth Studio | Unsloth Documentation
2+ mon, 3+ week 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+ mon, 3+ week ago (702+ words) Run & fine-tune NVIDIA Nemotron 3 Nano locally on your device! NVIDIA releases Nemotron-3-Nano-4 B, a 4 B open hybrid Mo E model that follows Nemotron-3-Super-120 B-A12 B and Nemotron-3-Nano-30 B-A3 B. The Nemotron family is designed for fast, accurate coding, math, and…...
Qwen3. 5 Fine-tuning Guide | Unsloth Documentation
3+ mon, 6+ day ago (624+ words) Learn how to fine-tune Qwen3. 5 LLMs with Unsloth. You can now fine-tune Qwen3. 5 model family (0. 8 B, 2 B, 4 B, 9 B, 27 B, 35 B'A3 B, 122 B'A10 B) with Unslotharrow-up-right. Support includes both vision and text fine-tuning. Qwen3. 5'35 B'A3 B - bf16 Lo RA works on 74 GB VRAM. Unsloth makes…...