We're excited to introduce Unsloth🦥Studio! 1. Chat UI has auto healing tool calling, Python & bash code execution, web search, image, docs input more! 2. Finetune audio, vision, LLMs with an AI Assist data prep 3. Supports GGUFs, Mac, Windows, Linux audio gen 4. Has SVG rendering, export to GGUF 5. gpt-oss harmony rendering, all inference params pre-set 6. Data designer synthetic data generation 7. Fast parallel data prep embedding finetuning 8. And much much more! To get it, run: pip install unsloth unsloth studio setup unsloth studio -H 0.0.0.0 -p 8888

Moderating the Model Compression panel with @mervenoyann @danielhanchen @parthsareen and Asma!

We'll be at AIEWF Thursday at the Local AI Summit (Room 2009) and roaming around! Can catch up / chat anytime! Plus we have some Unsloth cool merch!

We'll be at Room 2002 Moscone W 2:20PM at AIE today! A slide from the workshop showing if hypothetically reasoning / O-1 preview wasn't found - AI might have plateaued with a S shape vs now. And also how like Moore's Law, AI improvement is like a self fulfilling prophecy!

DeepSeek just released DSpark for V4 Flash & Pro, a new speculative decoding method boosting throughput by 51% to 400%! DS also showed DSpark works well for other models like Gemma & Qwen Github: github.com/deepseek-ai/DeepS… Paper: github.com/deepseek-ai/DeepS… HF: huggingface.co/deepseek-ai/D…

I'll be at @aiDotEngineer World's Fair next 29th giving a workshop on: 1. Kernels, torch.compile, Triton, auto kernels 2. RL, Reward Hacking, Continual Learning 3. Open v closed source 4. Benchmaxxing Unsloth merch! Room 2003 - 29th June 2:20pm-5:30pm. ai.engineer/worldsfair/sched…

What’s your go-to local model right now?

icymi we are doing a joint livestream with @UnslothAI to onboard you to open models 🔥 we cover from inference engines to open harnesses, so make sure not to miss! tune in tomorrow 8AM PST/5PM CEST @huggingface X and YT 🤗

Come join Thursday 8AM PST! I'll talk about GGUFs, quantization, GLM 5.2 quants, llama.cpp / llama-server & much more! Also ask any questions in the AMA / Q&A!

1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF: huggingface.co/unsloth/GLM-5…

I’m running a 3 hour advanced workshop at AI Engineer World’s Fair! 🚀 2026 has greatly changed how one should learn lower-level technicals like kernels, agentic RL, reward hacking, cont learning. What would you like to see? Last year @aiDotEngineer: youtube.com/watch?v=OkEGJ5G3…

GLM 5.2 dynamic 1-bit GGUF one shot Flappy Bird with 0 syntax errors whilst being 86% smaller! I was very surprised since normally 1-bit quants get syntax errors & you have to say "Fix bugs". UD 1-bit retained 76.2% top-1% accuracy whilst being 86% smaller vs BF16!

GLM-5.2 can now be run locally!🔥 The 2-bit model retains ~82% accuracy after we shrunk it from 1.51TB to 238GB (-84% size). Run on a 256GB Mac or RAM/VRAM setups. GLM-5.2 is the strongest open model to date. Guide: unsloth.ai/docs/models/glm-5… GGUF: huggingface.co/unsloth/GLM-5…

You can now run Kimi K2.7 Code locally! 🌘 We shrank the 1T model to 325GB (-48%) via Dynamic 2-bit where important layers are upcasted. Run at >40 tok/s on 330GB RAM/VRAM setups. Run full precision on 610 GB. Guide: unsloth.ai/docs/models/kimi-… GGUF: huggingface.co/unsloth/Kimi-…

ROCm has come a long way. And we are looking forward to what's coming next🚀🚀🚀 . Thanks @danielhanchen @UnslothAI

Local AI in action! MiniMax M3 unning locally on a single M3 Ultra 512GB in Unsloth Studio! 🔥 Here UD-Q5_K_XL decoding at 32.5 toks/s!

MiniMax M3 can now be run locally!🔥 MiniMax-M3 is a new 428B (23B active) open model with 1M context that performs on par with Gemini 3.1 Pro. Run Dynamic 2-bit GGUF on 138GB RAM/VRAM or 3-bit on 165GB. GGUF: huggingface.co/unsloth/MiniM… Guide: unsloth.ai/docs/models/minim…

Also new bypass permissions confirm tool calls - bypass permissions will allow the model to not use our AST based sandbox - be extra careful though!

Example of RAG support - we optimized it for small and large models, and you can tune the similarity metrics as well! GGUFs sentence-transformers are supported!

We added many features into Unsloth Studio! > Diffusion Gemma with canvas visualization! > Experimental RAG, Artifacts, Tensor Parallelism > Auto MTP, audio input, Cloudflare tunneling > 90% less tool call nudges with same acc > Bypass Perms for tool calls, update button more!

DiffusionGemma can now run at 2000 tokens/sec! ⚡ We made local DiffusionGemma inference 1.8× faster. Run it on 18GB RAM via Unsloth Studio. GitHub: github.com/unslothai/unsloth Guide: unsloth.ai/docs/models/diffu…