10 Ready Templates
AI Templates
No CUDA setup. Pick a template, choose your GPU — running in minutes.
Most Popular
🦙
Ollama
LLM ServeRun any open-source LLM with one command
Min 8GB VRAM
⚡
vLLM
LLM ServeHigh-throughput OpenAI-compatible inference server
Min 16GB VRAM
🤗
Text Generation Inference
LLM ServeHuggingFace production LLM serving
Min 16GB VRAM
🚀
SGLang
LLM ServeStructured generation & fast batching
Min 16GB VRAM
Most Popular
🌐
Open WebUI
UIChatGPT-style interface for Ollama / OpenAI
Min 8GB VRAM
💬
LibreChat
UIMulti-provider AI chat with plugins
Min 8GB VRAM
🔄
Flowise
UIDrag-and-drop LLM flow builder
Min 4GB VRAM
🪓
Axolotl
TrainingEasy LLM fine-tuning: LoRA, QLoRA, FSDP
Min 24GB VRAM
Fast
🦥
Unsloth
Training2× faster fine-tuning, 70% less VRAM
Min 16GB VRAM
🔗
Langflow
AgentVisual multi-agent & RAG pipeline builder
Min 8GB VRAM