Unsloth Desktop Launches: Train & Run 500+ Local Models, 70% Less VRAM
danielhanchen · x · 2026-09-17
Unsloth released Unsloth Desktop, the first open-source desktop app to run and train models locally (Mac/Windows/Linux), plus an official Docker image supporting 500+ models with no setup on NVIDIA and AMD GPUs.
- Trains models 2× faster with 70% less VRAM; supports MLX, diffusion image/video, audio, GGUF
- Connect Claude Code and Codex to local LLMs; sandboxed code exec, private web search, RAG, MCP
- OpenAI-compatible API and secure remote deployment
- Docker exposes ports 8000 (Studio) and 8888 (JupyterLab); needs NVIDIA driver 570.26+
Repo, blog and install guide are public.
Related event: Unsloth Desktop Brings Local Training of 500+ Models(2 posts)→
More from coding & agent
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02