Unsloth launches desktop app to run and train LLMs locally
thisdudelikesAI · x · 2026-09-16
Unsloth, the popular fine-tuning toolkit (76.2k GitHub stars), released its first native desktop app for running and training LLMs and diffusion models locally. Key points:
- Platforms: native downloads for Windows, macOS, Linux (deb/AppImage), plus a one-line curl install script for macOS/Linux/WSL
- Model support: GGUF and MLX formats, covering a wide range of open models (Qwen, DeepSeek, Gemma, FLUX and more)
- What it does: combines a local UI for running models with Unsloth's training capabilities, so users can fine-tune without notebooks or cloud
The project remains open source with 6.9k forks and 8,600+ commits, marking a shift from a notebook-centric workflow to a consumer-style desktop experience.
More from coding & agent
- Google Engineers' WikiSkill Turns Agent Execution History Into Validated, Reusable Skills — blaizedsouza · 2026-09-16
- Open Notebook: a free, local-first open-source NotebookLM alternative on GitHub — thisguyknowsai · 2026-09-16
- Indie dev open-sources Qwen-2.5-1B-RLCD with 5x faster on-device JSON inference — suchenzang · 2026-09-16
- FDE means three different jobs: Palantir veteran separates real product work from rebranded consulting — yangyi · 2026-09-16
- AI-Generated Tools Are Transforming Game Modding, Lowering the Entry Barrier — SuperSlowmia · 2026-09-16
- After two resets, a ChatGPT Pro 20x quota is down to 14% from heavy Codex use — craigbalding · 2026-09-16