Llama Models

Browse and run open-source AI models locally on your own hardware — no API keys, no cloud, no usage limits. Fully private, works offline, and free forever.

Llama running in Atomic Chat
Qwen3.6 27B MTP
27B
No models found
Reasoning
Code
Multilingual
Web
Vision
Thinking
Tools
Audio
Visuals
Embedding
Llama-3.2-3B-Instruct

Llama 3.2 3B Instruct is Meta's 3.21B multilingual chat model with a 128K context. The 4-bit GGUF build is a 2 GB file.

Tools
Reasoning
Code
Multilingual
Llama-3.1-8B-Instruct

Llama-3.1-8B-Instruct is Meta's 8B multilingual chat model with a 128K context and tool calling. The Q4_K_M build is 4.92 GB.

Tools
Reasoning
Code
Multilingual