Step 1 of 3
What is your primary use case?
Select the task that represents 80%+ of what you'll use the model for.
💬
Chat / Assistant
Conversational AI, customer support, general Q&A
💻
Code Generation
Write, explain, debug code — Python, JS, Go
📖
RAG / Knowledge Base
Retrieve and summarize long documents
🔬
Research / Reasoning
Complex multi-step reasoning, PhD-level questions
🌍
Multilingual
Support for non-English languages
🏎️
Edge / On-device
Must run on laptop/mobile without cloud
What hardware will you run it on?
This helps us filter out models that won't fit in your memory.
☁️
Cloud / API
Use via API, no local hardware constraints
🖥️
High-end GPU
RTX 4090, A100, 80GB+ VRAM
💻
Mid-range GPU
RTX 3080/4070, 16-24GB VRAM
🥔
Potato
CPU only or 8GB RAM — must be tiny
What's your priority?
Trade-off between quality and speed.
🏆
Best quality
Highest possible score, I don't care about speed
⚡
Balanced
Good quality + reasonable speed
🚀
Speed first
Fastest inference, good enough quality
Top Recommendations
Based on your selections:
Analyzing models...