Unsloth
Fine-tune LLMs faster with less memory.
Open-source library for fast, memory-efficient fine-tuning and RL of open models on a single GPU.
- Vendor
- Unsloth AI
- Category
- Data & ML platforms
- Pricing
- Open source
- Open source
- Yes
- License
- Apache 2.0
- Platforms
- Python, Colab
- Launched
- 2023
- Website
- unsloth.ai
Features
- 2x faster training
- Low VRAM
- GRPO / RL
Best for
- Local & on-device
More data & ml platforms
- Hugging Face — Hugging Face. The home of open models and datasets.
- Weights & Biases — Weights & Biases. The AI developer platform.
- Scale AI — Scale AI. Data labeling and evaluation for frontier AI.
- TRL — Hugging Face. Post-training library: SFT, DPO, GRPO and RL for LLMs.
- Label Studio — HumanSignal. Open-source data labelling for text, images, audio and LLM outputs.
- Axolotl — Axolotl AI. Config-driven fine-tuning for open LLMs.