unslothai/unsloth
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.
What it is
The Unsloth Docker image unsloth/unsloth is available on Docker. Read guide. Unsloth works on Windows, Linux, WSL and macOS. We support Multi GPU setups, NVIDIA, AMD, Intel GPUs, CPUs and the Vulkan backend. Run and train LLMs, MLX, GGUF, diffusion, decision, embedding, audio models: Qwen3.8, GLM-5.3-Flash, Kimi K3, Qwen-Image-2.1, MiniMax-H3, DeepSeek-V4, Gemma 4. Agents & Tools:** Use local models with Claude Code, Codex, and MCP, including tool calling and code execution. Browser use:** Navigate sites, fill out forms, read PDFs, and edit files beside your chat with a local model. Sandboxing:** Restrict which files your model can access when it runs commands in a sandbox. Search & RAG:**…
When to use it
Reach for unsloth when you need to call, serve, run locally, fine-tune or chat with a language model — it's written in Python and fits stacks tagged ai-agents, ai, chatgpt, deepseek.
