Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Update README.md
Michael Han06f9f1362985
diff --git a/README.md b/README.mdindex 5e9599e6329..d89d7d4ff97 100644--- a/README.md+++ b/README.md@@ -83,7 +83,7 @@ The [Unsloth Docker image](https://hub.docker.com/r/unsloth/unsloth) `unsloth/unUnsloth works on **Windows, Linux, WSL** and **macOS**. We support **Multi GPU setups, NVIDIA, AMD, Intel GPUs, CPUs** and the **Vulkan** backend.### Run & Build with AI-* Run and train LLMs, MLX, GGUF, diffusion, embedding, audio models: [Qwen3.8](https://unsloth.ai/docs/models/qwen3.8), [GLM-5.3-Flash](https://unsloth.ai/docs/models/glm-5.3-flash), [Kimi K3](https://unsloth.ai/docs/models/kimi-k3), [Qwen-Image-2.1](https://unsloth.ai/docs/models/qwen-image-2.1), MiniMax-H3, [DeepSeek-V4](https://unsloth.ai/docs/models/deepseek-v4), [Gemma 4](https://unsloth.ai/docs/models/gemma-4).+* Run and train LLMs, MLX, GGUF, diffusion, decision, embedding, audio models: [Qwen3.8](https://unsloth.ai/docs/models/qwen3.8), [GLM-5.3-Flash](https://unsloth.ai/docs/models/glm-5.3-flash), [Kimi K3](https://unsloth.ai/docs/models/kimi-k3), [Qwen-Image-2.1](https://unsloth.ai/docs/models/qwen-image-2.1), MiniMax-H3, [DeepSeek-V4](https://unsloth.ai/docs/models/deepseek-v4), [Gemma 4](https://unsloth.ai/docs/models/gemma-4).* **Agents & Tools:** Use local models with [Claude Code](https://unsloth.ai/docs/basics/claude-code), [Codex](https://unsloth.ai/docs/basics/codex), and [MCP](https://unsloth.ai/docs/basics/mcp), including tool calling and code execution.* **Search & RAG:** Use private and unlimited web search, deep research, auto-compaction (rolling context window) and RAG.* **Image and video:** Run and train [image](https://unsloth.ai/docs/basics/diffusion-image) and video diffusion or multimodal models@@ -92,7 +92,7 @@ Unsloth works on **Windows, Linux, WSL** and **macOS**. We support **Multi GPU s### Train & Deploy-* **Fine-tuning:** Train LLMs, diffusion, TTS, and embedding models 2× faster with 70% less VRAM with [no accuracy loss](https://unsloth.ai/blog#training)+* **Fine-tuning:** Train LLMs, diffusion, decision, TTS, and embedding models 2× faster with 70% less VRAM with [no accuracy loss](https://unsloth.ai/blog#training)* **Complete support:** Supports [reinforcement learning](https://unsloth.ai/docs/get-started/reinforcement-learning-rl-guide), LoRA, QLoRA, full fine tuning, pretraining, RL, GRPO, DPO, and FP8.* **Export & Deploy:** [Export](https://unsloth.ai/docs/new/studio/export) or Deploy models including [GGUF](https://unsloth.ai/docs/basics/inference-and-deployment/saving-to-gguf), NVFP4, FP8 and more formats.* **Datasets:** Build datasets from PDFs, CSVs, DOCX files, and more with [Data Recipes](https://unsloth.ai/docs/new/studio/data-recipe).