Repo RadarNewsletter

Trending/LLM & models

LLM & modelsAgents & orchestrationMCP servers

unslothai/unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

★ 78.8KWeek rank 135 · star gain starts at the next snapshot

View on GitHub

From the README

Unsloth is the first desktop app to run and train models. Features • Quickstart • Notebooks • Documentation ⚡ Get started Download the native Unsloth Desktop app for your operating system: Platform Link Windows Download macOS Download Linux / Ubuntu (deb) Download Linux / Ubuntu (ARM64) (deb) Download Linux (AppImage) Download Windows (ARM64) Download Download from Unsloth or GitHub Releases.

Setup prompt

Paste this into Cursor or Claude Code. It only includes install lines found in the README, and it asks the agent to review the code first.

Set up the GitHub repository unslothai/unsloth (Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.).
Repository: https://github.com/unslothai/unsloth

Official install commands found in the README:
curl -fsSL https://raw.githubusercontent.com/unslothai/unsloth/main/docker/install_nvidia_toolkit.sh -o install_nvidia_toolkit.sh && sudo -E bash install_nvidia_toolkit.sh
docker run -d --name unsloth --gpus all --ipc=host \
uv venv unsloth_env --python 3.13
uv pip install unsloth --torch-backend=auto

Clone the repository and follow those steps. Do not invent package names or extra install commands.
A remote shell one-liner from a third-party domain was omitted. Do not pipe remote scripts to a shell.
Review the code before running anything.

Buzz by window

Same mentions, three half-lives. This is not a star history. Star gain appears after a second daily snapshot.

  • Today0.09
  • Week0.94
  • Month1.30

Spotted on

Related

Report a problem or request removal