EmbeddingGemma 2: an open, lightweight multimodal embedding model
deepmind.google·6d ago
AI Engineering
Hacker News·11d ago·5 min read
Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
TL;DR
Janus is a Go-based binary that enables running GGUF models on local machines using Vulkan, supporting AMD, Intel, and Nvidia GPUs. It provides an OpenAI-compatible API and a web UI, allowing flexible integration without the need for Python or Docker.
✦ Why It Matters
Start using Janus today to run GGUF models locally without complex dependencies.
Key Takeaways
- Install Janus to run GGUF models locally on your machine.
- Utilize the built-in web UI for easy model interaction.
- Switch models dynamically without restarting the application.
- Integrate Janus with existing tools or scripts using its API.
How It Works
Janus operates as a single Go binary that leverages Vulkan for GPU-accelerated inference, allowing it to efficiently run GGUF models. It routes requests and executes tasks locally, providing an OpenAI-compatible API for seamless integration with various applications.
Users can interact with the models through a web interface or command line, making it versatile for different workflows.