TinyLlama 1.1B - FREE
100% Local

9 Premium Open Source Models

3 free models to start with, plus 6 pro models with license

TinyLlama 1.1B ⚡
637 MB • Pre-installed
✓ INSTALLED
Your instant-start AI companion. Lightweight and fast, perfect for quick conversations and getting started immediately.
💻 Requires: ~2GB RAM • Runs on any modern computer
Instant Start Quick Q&A Fast Responses
Llama 3.2 3B
2.0 GB
Not Installed
Meta's latest model with excellent balance of speed and intelligence. Great for everyday conversations and creative tasks.
💻 Requires: ~4-6GB RAM • Best with 8GB+ system RAM
Conversations Writing Analysis
Llama 3.1 8B
4.7 GB
Not Installed
Powerful and versatile model with excellent reasoning capabilities. Perfect balance between performance and resource usage.
💻 Requires: ~8-10GB RAM • Recommended: 16GB system RAM
Complex Tasks Reasoning Analysis
CodeLlama 7B
3.8 GB
Not Installed
Specialized for code generation, debugging, and explanations. Supports all major programming languages with expert-level knowledge.
💻 Requires: ~8GB RAM • Best with 12GB+ system RAM
Code Generation Debugging Refactoring
Mistral 7B Instruct
4.1 GB
Not Installed
Excellent at following complex instructions and creative writing. Known for its nuanced understanding and expressive outputs.
💻 Requires: ~8GB RAM • Best with 12GB+ system RAM
Creative Writing Instructions Storytelling
Phi-3 Medium
7.9 GB
Not Installed
Microsoft's larger Phi model with enhanced capabilities. Exceptional performance on reasoning and mathematical tasks.
💻 Requires: ~10-12GB RAM • Recommended: 16GB system RAM
Mathematics Logic Science
Gemma 2 2B
1.6 GB
Not Installed
Google's ultra-efficient model. Lightning-fast responses without sacrificing quality. Perfect for real-time applications.
💻 Requires: ~3-4GB RAM • Works great on 8GB systems
Speed Quick Tasks Low Latency
Gemma 2 9B
5.5 GB
Not Installed
Google's larger Gemma variant with superior performance. Excellent for complex reasoning and multi-step problem solving.
💻 Requires: ~9-11GB RAM • Recommended: 16GB system RAM
Advanced Tasks Research Problem Solving
Phi-3.5 Mini
2.2 GB
Not Installed
Microsoft's long-context specialist with 128K token window. Analyze entire books or extensive codebases in one go.
💻 Requires: ~4-6GB RAM • Best with 8GB+ system RAM
Long Documents Book Analysis 128K Context
Qwen 2.5 7B
4.7 GB
Not Installed
Alibaba's coding powerhouse. Exceptional at programming tasks, technical documentation, and system design.
💻 Requires: ~8GB RAM • Best with 12GB+ system RAM
Coding Architecture Technical Docs
Deepseek Coder 6.7B
3.8 GB
Not Installed
Specialized coding model trained on 2 trillion tokens of code. Exceptional at code completion and generation.
💻 Requires: ~6-8GB RAM • Best with 12GB+ system RAM
Autocomplete Code Review Unit Tests

🚀 Need More Power?

Affiliate links - we earn a commission at no extra cost to you

☁️ Cloud GPU Inference

Deploy massive models with cloud GPUs

Hyperbolic Open-source cloud GPU for AI inference Free Tier Cerebras Ultra-fast AI on specialized hardware

Trusted Partners

Join thousands of developers building the future of local AI with our ecosystem partners.

🚀
LocalAI Core
The engine powering our studio. Drop-in replacement for OpenAI API.
🦙
Ollama
Get up and running with large language models locally.
🤗
Hugging Face
The AI community building the future. Source of our models.

Installing Model

Downloading and setting up...

0%
Starting download...
🔒

Unlock 8 More Premium Models

Get lifetime access to Llama 3.1 8B, CodeLlama, Mistral, and more for just $5