🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We partnered with AI at Meta on a free notebook that turns your documents into high-quality synthetic datasets using Llama! Features: • Parses PDFs, websites, videos • Use Llama to generate QA pairs + auto-filter data • Fine-tunes dataset with Llama 🔗colab.research.google.com/github/unsloth…

You can now fine-tune Qwen3 (14B) for free with our notebook! Unsloth makes Qwen3 finetuning 2x faster with 70% less VRAM and 8x longer context lengths - with no accuracy loss. Guide: docs.unsloth.ai/basics/qwen3-h… GitHub: github.com/unslothai/unsl… Colab: colab.research.google.com/drive/1_ZJD6xq…

AI meetup next Saturday 10th May 3pm in SF! Super pumped for this!! My bro and I will be there! I have some limited time Unsloth stickers and badges as well :)

.Qwen 3 is amazing but you know what's better? Your own fine-tuned Qwen-3. Learn how to use the awesome Unsloth AI which makes fine-tuning feel like a breeze once you have your "DATA IN ORDER". youtu.be/BJgjYhJf7h4

If you're running Qwen3 locally, this is worth a look. Unsloth AI's 30B quant scores 82.2% on MMLU-Pro (CS), same as Qwen3-32B, but runs 5× faster (~45 tok/s vs <10 tok/s). Source: Wolfram Ravenwolf

Fine-tune Qwen3, LLaMA 4, and Gemma 2x faster with 80% less VRAM! Unsloth AI is an open-source Python framework that accelerates and simplifies the fine-tuning of LLMs. 100% Open Source

We're releasing a new advanced GRPO notebook for Qwen3. Learn about: • Fine-tuning Qwen3-Base to enable reasoning • Proximity scoring (closer answers = reward) • Advanced GRPO templates • OpenR1 dataset • Prefinetuning to skip GRPO learning format 🔗colab.research.google.com/github/unsloth…

You can now fine-tune TTS models with Unsloth! Train, run and save models like Sesame-CSM and OpenAI's Whisper locally with our free notebooks. Unsloth makes TTS training 1.5x faster with 50% less VRAM. GitHub: github.com/unslothai/unsl… Docs & Notebooks: docs.unsloth.ai/basics/text-to…

Let's build our own reasoning LLM using Reinforcement fine-tuning (100% local):

You can now finetune Sesame-CSM (1B) for free with our notebook! Clone voices, learn new emotions, tones & styles. Unsloth makes TTS train 1.5x faster with -50% VRAM & 0 accuracy loss GitHub: github.com/unslothai/unsl… Guide: docs.unsloth.ai/basics/text-to… Colab: colab.research.google.com/github/unsloth…

Thank you Google for demoing how to fine-tune Gemma 3 with Unsloth, free on Colab! 🦥 #GoogleIO

Mistral releases Devstral, a new model for coding agents. Devstral-Small-2505 is now the #1 open-source LLM on SWE-Bench Verified. At 24B params & built with All Hands, it scores 46.8% on SWE-Bench V - beating GPT-4.1-mini. Run & finetune via our GGUFs: huggingface.co/unsloth/Devstr…

Learn how to fine-tune Llama-3.1 8B on MI300X GPUs using Unsloth — Get the details here! bit.ly/4jhVIzA Catch Unsloth AI CEO, Daniel Han, at Advancing AI 2025 on 6/12 to dive deeper into fast, efficient LLM training.

We just crossed 10 million monthly downloads on @HuggingFace! 🦥🤗 It's all thanks to you guys - the amazing community, model builders, and HF team! 💖

You can now run DeepSeek-R1-0528 with our Dynamic 1-bit GGUFs! 🐋 We shrank the full 715GB model to just 185GB (-75% size). We achieve optimal accuracy by selectively quantizing layers. DeepSeek-R1-0528-Qwen3-8B is also supported. GGUFs: huggingface.co/unsloth/DeepSe…

We made a repo with 100+ Fine-tuning notebooks all in once place! Has guides & examples for: • Tool-calling, Classification, Synthetic data • BERT, TTS, Vision LLMs • GRPO, DPO, SFT, CPT • Dataprep, eval, saving • Llama, Qwen, Gemma, Phi, DeepSeek 🔗github.com/unslothai/note…

Finetune DeepSeek-R1-0528-Qwen3 with GRPO using our free notebook! Our new reward function increases multilingual (or custom domain) response rates by 40%+. Unsloth makes R1 finetuning 2× faster with 70% less VRAM. GitHub: github.com/unslothai/unsl… Colab: colab.research.google.com/github/unsloth…

Mistral releases Magistral, their new reasoning models! Magistral-Small-2506 excels at mathematics and coding. You can run the 24B model locally with just 32GB RAM by using our Dynamic GGUFs. GGUFs to run: huggingface.co/unsloth/Magist…

We made a complete Guide on Reinforcement Learning for LLMs! Learn about: • RL's goal & why it's key to building intelligent AI agents • Why o3, Claude 4 & R1 use RL • GRPO, RLHF, DPO, reward functions • Training your own local R1 model via Unsloth 🔗docs.unsloth.ai/basics/reinfor…