Open-source LLMs by Meta
| Model | API ID | Release | Cutoff | Conf. | Status | Notes |
|---|---|---|---|---|---|---|
| Llama 3 (8B/70B) | meta-llama/Meta-Llama-3-8B | 2024-04 | 2023-03 | high | active | |
| Llama 3.1 (8B/70B/405B) | meta-llama/Meta-Llama-3.1-8B | 2024-07 | 2023-12 | high | active | 405B is largest open model at release. |
| Llama 3.2 (1B/3B/11B/90B) | meta-llama/Llama-3.2-1B | 2024-09 | 2023-12 | high | active | Includes vision (11B/90B) and lightweight (1B/3B) variants. |
| Llama 3.3 (70B) | meta-llama/Llama-3.3-70B-Instruct | 2024-12 | 2023-12 | high | active | 405B-level quality at 70B size. |
| Llama 4 Scout (17B-16E) | meta-llama/Llama-4-Scout-17B-16E-Instruct | 2025-04 | 2024-08 | medium | active | MoE. 109B total / 17B active params. |
| Llama 4 Maverick (17B-128E) | meta-llama/Llama-4-Maverick-17B-128E-Instruct | 2025-04 | 2024-08 | medium | active | MoE. 400B total / 17B active. Vision + text. |
Knowledge Cutoffs