## Introducing Unsloth Studio: a new web UI for local AI

You can also run your fine-tuned models by using [Unsloth's 2x faster inference](/content/docs/basics/inference-and-deployment/unsloth-inference/index.html).

### Resources
- [Unsloth Studio Chat](/content/docs/new/studio#run-models-locally/index.html)
- [llama.cpp - Saving to GGUF](/content/docs/basics/inference-and-deployment/saving-to-gguf/index.html)
- [vLLM](/content/docs/basics/inference-and-deployment/vllm-guide/index.html)
- [Ollama](/content/docs/basics/inference-and-deployment/saving-to-ollama/index.html)
- [LM Studio](/content/docs/basics/inference-and-deployment/lm-studio/index.html)
- [SGLang](/content/docs/basics/inference-and-deployment/sglang-guide/index.html)
- [Troubleshooting](/content/docs/basics/inference-and-deployment/troubleshooting-inference/index.html)
- [llama-server & OpenAI endpoint](/content/docs/basics/inference-and-deployment/llama-server-and-openai-endpoint/index.html)
- [Tool Calling](/content/docs/basics/tool-calling-guide-for-local-llms/index.html)
- [Run LLMs on your Phone](/content/docs/basics/inference-and-deployment/deploy-llms-phone/index.html)

Last updated 25 days ago.