Unsloth
Open-source LLM fine-tuning library and desktop app for running and training models locally, with a dual Apache-2.0 / AGPL-3.0 license split.
Tags
Description
Established project (GitHub since 2023; not a 2026 launch; not archived). Core Python package on PyPI as unsloth (2026.11.3 verified 2026-11-10), installable with uv pip install unsloth --torch-backend=auto. The README also documents a native desktop app (downloads, Homebrew cask, Winget, Docker image unsloth/unsloth) plus install.sh/install.ps1 scripts. Dual licensing per README: core package Apache-2.0; optional Unsloth Studio UI components under AGPL-3.0 (studio/LICENSE.AGPL-3.0). GPU/model weights and any hosted extras are separate. Do not treat marketing 'first desktop app' wording as an independently verified industry-first claim.
Agent access
Related
- Axolotl: Apache-2.0 post-training / fine-tuning framework for a wide range of LLMs, with CLI, YAML configs, Docker and distributed-training options.
- LLaMA-Factory: Apache-2.0 toolkit to fine-tune 100+ LLMs and VLMs via zero-code CLI and the LLaMA Board Gradio web UI.
Guides & comparisons
- RL environment libraries compared — NeMo Gym, OpenEnv and Verifiers (Comparison): Compare NeMo Gym, OpenEnv and Verifiers as libraries for writing and running RL environments: authoring model, isolation, documented trainers, install paths, licences and current versions. Distinct from Harbor/AgentEnv/Seahaven and from the agent RL stacks comparison.
- Fine-tuning frameworks compared — Axolotl, LLaMA-Factory and Unsloth (Comparison): Compare Axolotl, LLaMA-Factory and Unsloth as SFT, LoRA/QLoRA and preference-tuning frameworks for tool-use models: documented methods, config style, chat/tool datasets, hardware backends, licences and current versions. Cross-links the agent RL stacks comparison.
- Post-training a tool-use model — TRL, PEFT, and scale-out RL (Stack): A recommended post-training stack for chat and tool-use models: TRL and PEFT for SFT, LoRA/QLoRA, DPO and GRPO, with OpenRLHF and AReaL as the distributed and asynchronous RL options. Cross-links the fine-tuning frameworks and agent RL stacks comparisons.
Sources
- https://github.com/unslothai/unsloth
- https://github.com/unslothai/unsloth/blob/main/LICENSE
- https://github.com/unslothai/unsloth/blob/main/studio/LICENSE.AGPL-3.0
- https://pypi.org/project/unsloth/
- https://unsloth.ai/docs
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)