Meta AI company blog
The Llama 4 herd
We’re introducing Llama 4 Scout and Llama 4 Maverick, the first open-weight natively multimodal models with unprecedented context support and our first built using a mixture-of-experts (MoE) architecture.
- Points
- 1,235
- HN comments
- 658
- Submissions
- 1
- Cited by
- 11 commenters
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Apr 5, 2025 | The Llama 4 herd by georgehill | 1,235 | 658 |
Cited in comments
Linked from 12 Hacker News comments by 11 different people, from Apr 2025 to Sep 2026.
Most recent:
- vrganj · Sep 8, 2026
- vrganj · Aug 4, 2026
- saubeidl · Aug 4, 2025
- christianqchung · Apr 14, 2025
- pavelstoev · Apr 6, 2025
- spmurrayzzz · Apr 5, 2025
