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
- LangChain Rebuilds LangSmith Trace Filtering for Faster Agent Observability — LangChain · 2026-09-18
- LangChain rebuilds LangSmith trace filtering for faster, more precise agent debugging — LangChain · 2026-09-18
- Dev: The Smartest Model Isn't the Best at Writing Simple, Mergeable Code — timigod · 2026-09-18
- LinkedIn to present a PyTorch-native GPU retrieval engine powering feed and search — PyTorch · 2026-09-18
- Jev + Kimi K3 cascade classifies 100 fraud emails at 96% accuracy for $0.07 — nutlope · 2026-09-17
- AWS compares Bedrock RAG vector stores: OpenSearch vs pgvector vs S3 Vectors — AWS ML Blog · 2026-09-17