Skip to content

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.

Update README.md

Michael Han8149f57436e6
diff --git a/README.md b/README.md
index c94002b2817..ac2b2137d4a 100644
--- a/README.md
+++ b/README.md
@@ -118,6 +118,7 @@ unsloth start claude --model unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_XL
| --- | --- |
| Claude Code | `unsloth start claude` |
| OpenAI Codex | `unsloth start codex` |
+| Visual Studio Code | `unsloth start vscode` |
| DeepSeek Harness | `unsloth start dsh` |
| OpenCode | `unsloth start opencode` |
| Hermes Agent | `unsloth start hermes` |
@@ -268,6 +269,7 @@ Read our [guide](https://unsloth.ai/docs/get-started/fine-tuning-llms-guide). Ad
| Model | Free Notebooks | Performance | Memory use |
|-----------|---------|--------|----------|
| **Unsloth Studio** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/unsloth/blob/main/studio/Unsloth_Studio_Colab.ipynb) | | |
+| **Decision model (Qwen3.5-4B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_5_(4B)-Decision.ipynb) | 1.5x faster | 60% less |
| **Gemma 4 (E2B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma4_(E2B)-Vision.ipynb) | 1.5x faster | 50% less |
| **Qwen3.5 (4B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_5_(4B)_Vision.ipynb) | 1.5x faster | 60% less |
| **gpt-oss (20B)** | [▶️ Start for free](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt-oss-(20B)-Fine-tuning.ipynb) | 2x faster | 70% less |
@@ -283,31 +285,6 @@ Read our [guide](https://unsloth.ai/docs/get-started/fine-tuning-llms-guide). Ad
- See [all our models](https://unsloth.ai/docs/get-started/unsloth-model-catalog) and [all our notebooks](https://unsloth.ai/docs/get-started/unsloth-notebooks)
- See detailed documentation for Unsloth [here](https://unsloth.ai/docs)
-## 🦥 Unsloth News
-- **AMD training**: Train, run RL, chat and deploy on AMD GPUs across Windows, WSL and Linux. [Guide](https://unsloth.ai/docs/basics/amd)
-- **Local models for any agent**: Use `unsloth start` with Claude Code, Codex, Hermes, OpenCode, OpenClaw, DeepSeek Harness and more through Unsloth's OpenAI- and Anthropic-compatible APIs. [Guide](https://unsloth.ai/docs/basics/api)
-- **GLM-5.2**: Run Z.ai's 744B-parameter, 1M-context open model locally with Unsloth Dynamic GGUFs. [Guide](https://unsloth.ai/docs/models/glm-5.2)
-- **DeepSeek-V4**: Run DeepSeek-V4-Flash locally with corrected multi-turn and tool-calling behavior. [Guide](https://unsloth.ai/docs/models/deepseek-v4)
-- **Gemma 4**: Run and train Gemma 4 text, image and audio models with QAT, MTP, GGUF and MLX support. [Guide](https://unsloth.ai/docs/models/gemma-4)
-- **MCP servers**: Connect local models to files, apps, databases and external tools through Model Context Protocol. [Guide](https://unsloth.ai/docs/basics/mcp)
-- **New models**: [Qwen-AgentWorld](https://huggingface.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF), [Ornith](https://huggingface.co/unsloth/models?search=ornith), [Kimi K2.7 Code](https://unsloth.ai/docs/models/kimi-k2.7-code) and [MiniMax M3](https://unsloth.ai/docs/models/minimax-m3)
-
-<details>
- <summary>More News</summary>
-
- - **Connections**: Mix local models with API providers (OpenAI, Anthropic) or servers (vLLM, Ollama) in the same interface. [Guide](https://unsloth.ai/docs/integrations/connections)
- - **Introducing Unsloth Studio**: our new web UI for running and training LLMs. [Blog](https://unsloth.ai/docs/new/studio)
- - **DiffusionGemma**: Run and fine-tune Google's diffusion language model with 1.8x faster inference in Unsloth Studio. [Guide](https://unsloth.ai/docs/models/diffusiongemma)
- - **Qwen3.6**: Run and train Qwen3.6 with MTP for 1.4-2.2x faster inference and NVFP4 quants for supported GPUs. [Guide](https://unsloth.ai/docs/models/qwen3.6)
- - Train **MoE LLMs 12x faster** with 35% less VRAM - DeepSeek, GLM, Qwen and gpt-oss. [Blog](https://unsloth.ai/docs/new/faster-moe)
- - **Embedding models**: Unsloth now supports ~1.8-3.3x faster embedding fine-tuning. [Blog](https://unsloth.ai/docs/new/embedding-finetuning) • [Notebooks](https://unsloth.ai/docs/get-started/unsloth-notebooks#embedding-models)
- - New **7x longer context RL** vs. all other setups, via our new batching algorithms. [Blog](https://unsloth.ai/docs/new/grpo-long-context)
- - New RoPE & MLP **Triton Kernels** & **Padding Free + Packing**: 3x faster training & 30% less VRAM. [Blog](https://unsloth.ai/docs/new/3x-faster-training-packing)
- - **500K Context**: Training a 20B model with >500K context is now possible on an 80GB GPU. [Blog](https://unsloth.ai/docs/blog/500k-context-length-fine-tuning)
- - **FP8 & Vision RL**: You can now do FP8 & VLM GRPO on consumer GPUs. [FP8 Blog](https://unsloth.ai/docs/get-started/reinforcement-learning-rl-guide/fp8-reinforcement-learning) • [Vision RL](https://unsloth.ai/docs/get-started/reinforcement-learning-rl-guide/vision-reinforcement-learning-vlm-rl)
-
-</details>
-
## 📥 Advanced Installation
The below advanced instructions are for Unsloth Studio. For Unsloth Core advanced installation, [view our docs](https://unsloth.ai/docs/get-started/install/pip-install#advanced-pip-installation).