Local model running
Run GGUF and safetensors models locally, compare two models side by side, and use uploaded images, documents, audio, or code files in the workflow.
Unsloth
Freemium
Interface web local e framework de código aberto para treinar, executar e exportar modelos abertos no seu hardware
O que é Unsloth?
Unsloth is an open-source framework and local web UI for training, running, and exporting open models from one unified interface. The product is centered on keeping model workflows on your own hardware, with documentation that covers local inference, fine-tuning, data preparation, and export.
The Studio release adds a no-code local workflow for running GGUF and safetensors models, preparing datasets from files such as PDFs and CSVs, and training models with built-in observability. The site positions Unsloth as a way to work with 500+ models across text, vision, audio, and embeddings without leaving a local environment.
O que Unsloth pode fazer?
Dataset preparation
Auto-create datasets from PDFs, CSVs, JSON, DOCX, TXT, and YAML sources, then clean and refine them in the Data Recipes workflow.
Local training controls
Train and fine-tune 500+ models with LoRA, 4-bit, 16-bit, FP8, and pre-training options, with live observability for loss, gradient norms, and GPU usage.
Tool calling and code execution
Use self-healing tool calling, web search, Bash, and Python execution, including sandboxed code runs for testing and verification.
Model export
Export models to GGUF or safetensors for use with llama.cpp, vLLM, Ollama, LM Studio, and similar runtimes.
API access
Connect to Unsloth through an API endpoint or use it with external tools such as Claude Code and Codex, as described in the Studio docs.
Casos de uso
“Fine-tune models from local documents”
Prepare a local fine-tuning workflow by importing source files, converting them into datasets, and starting training with presets or custom settings.
“Local inference and evaluation”
Run a model offline on your own machine, compare outputs from two models, and test tool calling or web search in a controlled environment.
“Dataset creation and cleanup”
Turn unstructured files into training-ready datasets with Data Recipes, then refine the dataset in a visual node workflow before training.
“Model export for downstream tools”
Export a trained or base model to GGUF or safetensors so it can be used in runtimes such as llama.cpp, vLLM, Ollama, or LM Studio.
“Local API integration”
Use the API endpoint or connect external tools to a local model when you want local inference inside developer workflows.
Perguntas frequentes
What is Unsloth Studio?
Unsloth Studio is a local web UI for training, running, and exporting open models. The docs describe it as an open-source, no-code interface that works offline on your own machine.
Which operating systems does it support?
The docs say Unsloth Studio works on Windows, Linux, WSL, and macOS. It also supports NVIDIA GPUs for training, while CPU-only setups are limited to chat inference and Data Recipes.
What kinds of models can it handle?
Unsloth supports running and training models locally, exporting models to safetensors or GGUF, and using an API endpoint. The docs also mention support for text, vision, audio/TTS, and embedding models.
Does Unsloth have paid plans?
Yes. The pricing page includes a Free plan, a Pro plan, and an Enterprise plan. The free version is open source, while paid plans add higher-performance and enterprise capabilities.
Does Unsloth collect user data?
The Studio docs say Unsloth does not collect usage telemetry. It only collects minimal hardware information needed for compatibility, and Studio runs 100% offline and locally.
Informações rápidas
- Category
- AI Development Tool
- Product type
- Open-source local web UI and framework
- Primary use
- Train, run, and export models locally
- Platforms
- Windows, Linux, WSL, macOS; Docker also available
- Source domain
- unsloth.ai
- Pricing
- Free plan, Pro plan, and Enterprise plan
Análise de tráfego de Unsloth
Os dados de tráfego são apenas para referência.
- Classificação do domínio
- 76
Alternativas ao Unsloth
Ludwig
ludwig.ai
Framework declarativo de deep learning de código aberto para treinar, ajustar e implantar modelos com uma única configuração YAML.
OpenFang
openfang.sh
OpenFang é um sistema operacional de agentes de código aberto, desenvolvido em Rust, para executar, configurar e supervisionar agentes autônomos. Oferece implantação local ou autogerenciada, modelos integrados, manifestos personalizados, canais de mensagens e controle por navegador ou API.
TensorFlow
tensorflow.org
Plataforma de machine learning de código aberto para criar, treinar e implantar modelos em desktop, dispositivos móveis, web, nuvem e edge.
TalkCody
talkcody.com
TalkCody é um agente de programação com IA gratuito e de código aberto para macOS, Windows e Linux, com vários provedores de modelos, armazenamento local e fluxos offline.
Craft Agents
agents.craft.do
Craft Agents é uma aplicação desktop de código aberto para trabalhar com agentes de IA, conectando modelos, APIs, servidores MCP, ficheiros locais e um navegador integrado.
OpenHands
openhands.dev
OpenHands é uma plataforma de código aberto e agnóstica em relação a modelos para agentes de programação na nuvem, que automatiza fluxos de engenharia por meio de interfaces web, CLI, terminal UI e SDK, com implantações locais, na nuvem e empresariais.