Unsloth AI

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

TIL that you can install @UnslothAI Studio in @GoogleColab, then launch the UI backed with the notebook! 🤯🦥

Mistral releases Mistral Medium 3.5, a new vision reasoning model. 🔥 Mistral-Medium-3.5-128B offers highly competitive performance for models 6x its size. Run locally on ~64GB RAM. Guide: unsloth.ai/docs/models/mi… GGUFs: huggingface.co/unsloth/Mistra…

NVIDIA releases Nemotron-3-Nano-Omni, a new 30B open multimodal MoE model. Nemotron-3-Nano-Omni-30B-A3B is the strongest omni model for its size and supports audio, video, image and text. Run on ~25GB RAM. GGUF: huggingface.co/unsloth/NVIDIA… Guide: unsloth.ai/docs/models/ne…

@huggingface 🦥🤝🤗

@UnslothAI congrats, 1000 times deserved!

Unsloth is now one of the top 10 most followed organizations on Hugging Face. 🤗🦥 Thanks so much for all the support!

@NVIDIAAI @huggingface Thank you NVIDIA for always helping open-source! 💚🙏

@UnslothAI @huggingface No surprise there - we 💚 Unsloth.

DeepSeek releases DeepSeek-V4. 🐋 - DeepSeek-V4-Pro: 1.6T params - DeepSeek-V4-Flash: 284B params DeepSeek-V4-Pro rivals Claude-Opus-4.6-Max, GPT-5.4-xHigh and Gemini-3.1-Pro-High. They support 1M context length, thinking and set new records for Codeforces.

@deepseek_ai Thanks for continuing to release open-source models! Hopefully you guys will release smaller models soon so we can run it locally. 🙏♥️

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n

2-bit Qwen3.6-27B GGUF made 26 tool calls, triaged 15 GitHub issues and fixed, tested + reproed our repo’s 3 latest issues. 🔥 Try this locally in Unsloth Studio with just 12GB RAM. Studio also has a new look! GitHub: github.com/unslothai/unsl…

@Alibaba_Qwen Thanks so much for releasing such brilliant models. We're excited for more bigger and smaller models! 😍

⚡️⚡️Run Qwen3.6-27B locally! @UnslothAI

@Alibaba_Qwen Qwen3.6-27B MLX quants for macOS are available here: #mlx-dynamic-quants" target="_blank" rel="nofollow noopener">unsloth.ai/docs/models/qw… The rest of the Qwen3.6-27B GGUFs are now uploaded as well, including BF16 and Q8. 🙏

Qwen3.6-27B can now run locally! 💜 Run on 18GB RAM via Unsloth Dynamic GGUFs. Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks. GGUFs: huggingface.co/unsloth/Qwen3.… Guide: unsloth.ai/docs/models/qw…

@Alibaba_Qwen This model is amazing, thank you Qwen! 🥰 We are working on Qwen3.6-27B Dynamic GGUFs so you all can run it locally: huggingface.co/unsloth/Qwen3.…

🚀 Meet Qwen3.6-27B, our latest dense, open-source model, packing flagship-level coding power! Yes, 27B, and Qwen3.6-27B punches way above its weight. 👇 What's new: 🧠 Outstanding agentic coding — surpasses Qwen3.5-397B-A17B across all major coding benchmarks 💡 Strong reasoning across text & multimodal tasks 🔄 Supports thinking & non-thinking modes ✅ Apache 2.0 — fully open, fully yours Smaller model. Bigger results. Community's favorite. ❤️ We can't wait to see what you build with Qwen3.6-27B! 👀 🔗👇 Blog: qwen.ai/blog?id=qwen3.… Qwen Studio: chat.qwen.ai/?models=qwen3.… Github: github.com/QwenLM/Qwen3.6 Hugging Face: huggingface.co/Qwen/Qwen3.6-2… huggingface.co/Qwen/Qwen3.6-2… ModelScope: modelscope.cn/models/Qwen/Qw… modelscope.cn/models/Qwen/Qw…

Kimi K2.6 can now run on CPU, GPU and SSD setups! 🔥 We shrank the 1T model to 340GB via Dynamic GGUFs where important layers are upcasted. Run at >40 tok/s on 350GB RAM/VRAM setups. Run full precision on 610 GB. Guide: unsloth.ai/docs/models/ki… GGUF: huggingface.co/unsloth/Kimi-K…

@Kimi_Moonshot Congrats guys on another epic open-source release! 🔥 We're working on Kimi-K2.6 Dynamic GGUFs so folks can run it locally (if you have enough compute): huggingface.co/unsloth/Kimi-K…

Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…

We benchmarked Gemma 4 26B-A4B GGUFs to identify the best performing quants. Unsloth ranks first in ALL 22 of 22 model sizes on mean KL divergence, making them SOTA. GGUFs: huggingface.co/unsloth/gemma-…

We ran Qwen3.6-35-A3B GGUF performance benchmarks to help you choose the best quant. Unsloth ranks first in 21 of 22 model sizes on mean KL divergence, making them SOTA. GGUFs: huggingface.co/unsloth/Qwen3.…