Unsloth
A local interface and command-line tool for running and fine-tuning language and diffusion models.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About Unsloth
Unsloth lets you run and train large language models and diffusion models on your own hardware. The project provides a local UI (Unsloth Studio) along with a command-line tool, and it works with GGUF and MLX model formats as well as model families such as Qwen, DeepSeek, Gemma and FLUX.
Install scripts are provided for Linux and macOS shells and for Windows PowerShell, and a Docker setup is included. It suits people who want to adapt an open model to their own data without renting cloud training services.
Strengths
- Both running and fine-tuning models in one tool
- Local UI as well as a command-line interface
- Supports GGUF and MLX formats and many current model families
- Install scripts for Windows, macOS and Linux, plus Docker
Limitations
- Fine-tuning needs capable hardware, typically a strong GPU
- The research does not state the license
Details
- Pricing
- FreeFree to download and use from its GitHub repository.
- License
- Proprietary
- Developer
- Unsloth AI
- Platforms
- Windows, macOS, Linux, Command line
- How it runs
- Downloadable app
- Best suited for
- People who want to fine-tune or run open models on their own machine
- Categories
- Local AI tools, Developer tools
- Last verified
- Added
- Provenance
- Facts checked against the developer's own pages and store listings, 1 sources on file.
Alternatives to Unsloth
Compare allSoftware that can replace Unsloth for an important use case, and what changes if you switch.
LlamaFactory
Web UI and command-line toolkit for fine-tuning over 100 open language and vision-language models.
LlamaFactory is Apache-2.0 with a web UI and command line for fine-tuning over 100 models, but focuses on training rather than running.
Axolotl
A command-line tool for fine-tuning language models from YAML configuration files.
Axolotl is an Apache-2.0 Linux command-line fine-tuning tool driven by YAML configuration files, with no local UI.
MLX LM
A Python package and command-line tool for running and fine-tuning language models on Apple silicon.
MLX LM runs and fine-tunes language models on Apple silicon only, from the command line or Python, without a graphical interface.
Similar software
Related functionality, not necessarily a direct replacement.
Kohya's GUI
A local graphical interface for training LoRA models and fine-tuning Stable Diffusion image models.
Ollama
The simplest way to pull down an open language model and run it on your own machine, from one command or a desktop app.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
LM Studio
A polished desktop app for downloading, running and chatting with local language models, with an OpenAI-compatible server built in.
nvitop
Interactive terminal viewer for NVIDIA GPUs and the processes running on them.
