Lemonade by AMD: Open Source Local LLM Server for GPU and NPU
What Lemonade Is
Lemonade is a local AI server built by AMD and the local AI community that runs text, image, and speech models on GPUs and NPUs. It's open source, designed to be private, and claims to be ready in minutes on any PC.
Key Features and Specifications
- Native C++ Backend: Lightweight service that is only 2MB
- One Minute Install: Simple installer that sets up the stack automatically
- OpenAI API Compatible: Works with hundreds of apps out-of-box and integrates in minutes
- Auto-configures for your hardware: Configures dependencies for your GPU and NPU
- Multi-engine compatibility: Works with llama.cpp, Ryzen AI SW, FastFlowLM, and more
- Multiple Models at Once: Run more than one model at the same time
- Cross-platform: A consistent experience across Windows, Linux, and macOS (beta)
- Built-in app: A GUI that lets you download, try, and switch models quickly
- Unified API: One local service for every modality including chat, vision, image generation, transcription, and speech generation
Model Support and Performance
The server can load models like gpt-oss-120b or Qwen-Coder-Next for advanced tool use. For tuning, you can use --no-mmap to speed up load times and increase context size to 64 or more. The source mentions that with 128 GB of unified RAM, you can load larger models.
Ecosystem Integration
Lemonade is integrated in many apps and works out-of-box with hundreds more thanks to the OpenAI API standard. Mentioned integrations include Open WebUI, n8n, Gaia Infinity, Arcade, GitHub Copilot, OpenHands, Dify, Deep Tutor, and Iterate.ai.
Community and Development
The project has 2.1k stars on GitHub and an active Discord community with 117 online at the time of the source. It's described as being built by the local AI community for every PC, with the philosophy that local AI should be free, open, fast, and private.
📖 Read the full source: HN LLM Tools
👀 See Also
SoulPrint: Local Tool for Searching Claude and ChatGPT History Together
SoulPrint is an open-source Python tool that imports conversation exports from Claude (.json) and ChatGPT (.zip) into a local SQLite archive, enabling full-text search across both providers simultaneously with BM25 ranking and highlighted snippets.
Scaling Karpathy's Autoresearch with 16 GPUs: Results and Methods
The SkyPilot team gave Claude Code access to 16 GPUs on a Kubernetes cluster to run Karpathy's Autoresearch project. Over 8 hours, the agent submitted ~910 experiments, reduced validation bits per byte from 1.003 to 0.974 (2.87% improvement), and reached the best validation loss 9x faster than sequential execution.
Exploiting LLM Hidden Agency Signal (Â) for Better Tool Calling
A developer discovered that LLMs have a linearly separable hidden state direction called  that predicts tool calls with AUC > 0.94. Using this signal to force tool calls improved Qwen3-1.7B performance from 26.7% to 85% (+58% gain) and reduced no-tool failures from 43% to 2.6%.
NPCterm: Full PTY Terminal Emulator for AI Agents via MCP
NPCterm provides AI agents with full terminal access through a headless, in-memory PTY terminal emulator exposed via MCP. It includes 15 MCP tools for terminal control, process state detection, and support for TUI applications.