Skip to content

XTuner

A flexible fine-tuning toolkit for large models

Visit official site

What XTuner is

The toolkit is described as an efficient and flexible fine-tuning toolkit for large models, covering LLM and VLM training on almost any GPU.

What you can do with it

  • Fine-tune InternLM2 on a single GPU
  • Apply QLoRA to a ChatGLM3 model

What to watch out for

  • Training runs on GPU hardware
  • The chosen algorithm decides the fine-tuning path

Pros & cons

✓ What we like

  • QLoRA, LoRA and full parameter training are listed
  • LLM and VLM models including LLaVA are supported

! What to watch out for

  • Training runs on GPU hardware
  • The chosen algorithm decides the fine-tuning path

FAQ

Which training algorithms are supported?

The card lists QLoRA, LoRA and full parameter fine-tuning.

What performance features are named?

The card names FlashAttention, Triton kernels, DeepSpeed and ZeRO.

Last reviewed: 2026-11-15

More AI coding tools tools

View all →

How we review