Menu
mutinai
What can I run?
Public preview · figures are illustrative fixture data, attributed to their source · data to May 2025 · read-only
Tool · Fine-tuning framework · Unsloth AI

Unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

License
PermissiveApache License 2.0
Language
Python
Latest release
22 Sept 2026Unsloth Qwen-Image-2.1 + Skills
Measurements
0
RepositoryWebsite

Relationships

No relationships recorded.

Releases & news

  1. Unsloth Qwen-Image-2.1 + Skills
    You can now run Qwen-Image-2.1 locally with Unsloth! This release also includes custom Agent Skills, and easier chat/project management. It also brings 2x faster reasoning blocks (60 FPS vs 30 FPS), more reliable training, and improved Linux installs and updates. Qwen Image 2.1 G
  2. Unsloth Qwen-Image-2.1 + Skills
    We're releasing support for Qwen-Image-2.1, custom Agent Skills, and easier chat/project management. It also brings 2x faster reasoning blocks (60 FPS vs 30 FPS), more reliable training, and improved Linux installs and updates. Qwen Image 2.1 Guide
  3. Unsloth Docker + Multi User + AMD Support
    We're releasing our new updated Docker image along with multi-user accounts, RDNA1+2, FP8/INT8 diffusion support, ARM64 CUDA Windows support and many training, GRPO and inference improvements. Also a Qwen3.8-Flash-Next 2x faster MTP hotfix.
  4. Unsloth Docker + Multi User + AMD Support
    We're releasing our new updated Docker image along with multi-user accounts, RDNA1+2, FP8/INT8 diffusion support, ARM64 CUDA Windows support and many training, GRPO and inference improvements
  6. Unsloth Large Performance Gains + Fixes
    This is a large performance and reliability + bug fix release for Unsloth
  7. Unsloth Large Perf Improvements + Fixes
    This is a large performance and reliability + bug fix release for Unsloth
  8. Unsloth 2x Faster Qwen3.8-Flash + GLM-5.3-Flash MTP
    Run Qwen3.8-Flash-Next and GLM-5.3-Flash up to 2x faster with MTP. MTP is enabled by default, you can still disable it.
  9. Unsloth 2x Faster Qwen3.8-Flash + GLM-5.3-Flash MTP
    Run Qwen3.8-Flash-Next and GLM-5.3-Flash up to 2x faster with MTP. MTP is enabled by default, you can still disable it.
  10. Unsloth Qwen3.8-Flash-Next + GLM-5.3-Flash
    Qwen3.8-Flash-Next and GLM-5.3-Flash can now run locally in Unsloth!
  11. Unsloth Bug Fixes + Auto compaction + LAN Remote Access
    Thanks for the support for Qwen3.8-27B and Unsloth Desktop! This is a bug fix release with 170+ PRs.
  12. Unsloth Bug Fixes + Auto compaction + LAN Remote Access
    Thanks for the support for Qwen3.8-27B and Unsloth Desktop! This is a bug fix release with 170+ PRs.
  13. Unsloth Auto compaction (preview) + LAN Remote Access
    Thanks for the support for Qwen3.8-27B and Unsloth Desktop last week! For this release, we merged 200+ PRs to introduce many new features, fixes including:
  14. Unsloth Qwen3.8-27B
    Qwen3.8-27B and Qwen3.8-2.4T can now be run locally in Unsloth!
  15. Unsloth v0.1.702-beta
    Unsloth Desktop is here! The first desktop app to run and train AI models locally. Research, export and deploy from the same open-source app on Windows, macOS and Linux.

Reviews

Contributions are not open yet, so there is nothing here from members.

Sources & history

Sources

  • GitHub (live source, 6 records, 22 Sept 2026)

External identifiers

Field history

  • homepageUrl = "https://unsloth.ai/docs" — GitHub (current)
  • homepageUrl = "https://unsloth.ai/docs" — GitHub
  • homepageUrl = "https://unsloth.ai/docs" — GitHub
  • homepageUrl = "https://unsloth.ai/docs" — GitHub
  • homepageUrl = "https://unsloth.ai/docs" — GitHub
  • homepageUrl = "https://unsloth.ai/docs" — GitHub
  • primaryLanguage = "Python" — GitHub (current)
  • primaryLanguage = "Python" — GitHub
  • primaryLanguage = "Python" — GitHub
  • primaryLanguage = "Python" — GitHub
  • primaryLanguage = "Python" — GitHub
  • primaryLanguage = "Python" — GitHub