Llama
Meta's open-weight family.
At a glance
Current release
From the release row Llama 4.
Family record: Press release · 5 Sep 2026
Built on it
6 products in this catalogue name this family on their own pages.
-
Baseten Model APIs
Baseten
Official documentation · 5 Sep 2026 -
Cerebras Inference
Cerebras Systems
Official documentation · 5 Sep 2026 -
Fireworks AI
Fireworks AI
Official documentation · 5 Sep 2026 -
Nebius Token Factory
Nebius Group
Official documentation · 5 Sep 2026 -
SambaCloud
SambaNova
Official documentation · 5 Sep 2026 -
Together Inference
Together AI
Official documentation · 5 Sep 2026
Releases
-
LLaMA
Foundational model in 7B, 13B, 33B and 65B sizes, released under a noncommercial research license with access granted case by case to researchers.
-
Llama 2
Pretrained and fine-tuned chat weights released 'free for research and commercial use', with Microsoft as preferred partner on Azure and Windows.
-
Code Llama
Code-specialised Llama 2 in 7B, 13B and 34B with Python and Instruct variants under the Llama 2 community license; a 70B size was added January 29, 2024.
-
Llama 3
8B and 70B models pretrained on over 15T tokens, claimed the best open models of their class; a 400B+ model was still training at release.
-
Llama 3.1
Llama 3.1 405B, presented as the first frontier-level open model, with 128K context, eight languages and a license allowing outputs to train other models.
-
Llama 3.2
First vision Llama models (11B and 90B) plus 1B and 3B text models for edge and mobile devices with 128K context, announced at Connect 2024.
-
Llama 4
Natively multimodal mixture-of-experts models Scout (16 experts, 10M context claimed) and Maverick (128 experts) downloadable at release; Behemoth previewed, still training.