Launches · Project

Unsloth

Unsloth provides tools for running, fine-tuning and exporting open-weight models on local hardware.

+ Follow

Builder facts

  • Fine-tuning. The toolkit supports LoRA, 4-bit QLoRA and full fine-tuning, which needs more compute and memory. Source ↗
  • Export. Studio exports merged weights, adapter-only weights that require the original model, or GGUF files for local runtimes. Source ↗
  • Local access. Unsloth’s core is Apache-2.0 licensed, and the AGPL-3.0 Studio interface can operate offline. Source ↗
  • Provider access. Studio can connect to external providers using separate API keys from those providers. Source ↗

Sources checked

Publisher update ·

Unsloth 0.1.919 beta ↗

Adds local text translation and redesigns the model picker.

Change timeline

0 stories

No verified releases in this timeline yet.