Meta Releases Llama 3 8B as Open Source with Improved MMLU Performance
Meta has launched the Llama 3 8B language model as open source. The model achieves 68.5 points on the MMLU benchmark, surpassing its predecessor, Llama 2 7B.
What happened?
Meta has launched the AI model Llama 3 8B, featuring 8 billion parameters. The model was released as open source on 15 March 2024. In the MMLU performance test, the model achieved 68.5 points, outperforming its predecessor, Llama 2 7B, which recorded 63.2 points.
Key facts
| Modell | Llama 3 8B |
|---|---|
| Parametrar | 8 miljarder |
| Lanseringsdatum | 15 mars 2024 |
| MMLU-resultat Llama 3 8B | 68,5 poäng |
| MMLU-resultat Llama 2 7B | 63,2 poäng |
Why it matters
An increase of 5.3 points on the MMLU demonstrates clear performance improvements for models in the sub-10 billion parameter size class. This provides developers with access to more powerful open models that have lower computational requirements than large-scale alternatives.
Who is affected?
Developers, AI researchers, and organisations building applications based on open language models are directly affected by this release. Companies running smaller language models locally will also be impacted.
What else you should know
The source states that the model demonstrates a noticeable performance increase compared to the previous generation, with a 5.3-point improvement on the MMLU. The model was released as open source.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Decide whether this affects strategy over 6–12 months or is just noise.
- Discuss with leadership: do we own the right question or does ownership need to move?
- Ask: what risk are we taking by NOT acting on this this quarter?
Generated angle — not editorial analysis of "Meta Releases Llama 3 8B as Open Source with Improved MMLU P"