Skip to content
local-ai

Axolotl

Fine-tuning Advanced Open source Free

A config-driven fine-tuning framework where you describe a training run in a YAML file. It supports the full range of techniques, from LoRA and QLoRA to full fine-tunes and preference optimisation, and scales to multi-GPU setups.

Strengths

  • Reproducible, config-driven runs suited to serious workflows
  • Broad technique support, including alignment and preference tuning
  • Handles multi-GPU training, unlike single-GPU-focused tools

Weaknesses

  • The config-first approach has a learning curve
  • Real training runs still want proper GPU hardware
  • Less turnkey than a GUI tool for a first fine-tune

At a glance

Licence
Apache 2.0
Pricing
Free
Platforms
Linux
GPU required
Yes

Links

Works with

See also

Entry last verified 30 July 2026.