Loading...
Loading...
Browse all stories on DeepNewz
VisitHow many downloads will DeepSeek-V3 have on Hugging Face by end of 2025?
Less than 100,000 • 25%
100,000 to 500,000 • 25%
500,001 to 1,000,000 • 25%
More than 1,000,000 • 25%
Download statistics from Hugging Face platform
DeepSeek Launches Open-Source V3 Model with 671 Billion Parameters, 60 Tokens/Second, and $5.6 Million Training Cost
Dec 26, 2024, 03:08 PM
DeepSeek has officially released its latest AI model, DeepSeek-V3, which features 671 billion parameters and is designed with a Mixture-of-Experts (MoE) architecture. This model is reported to be three times faster than its predecessor, achieving a processing speed of 60 tokens per second. DeepSeek-V3 has already demonstrated superior performance on the Aider polyglot leaderboard, securing second place with a score of 48%, surpassing Sonnet 3.5 and other models. The model was trained on 14.8 trillion tokens and utilizes 256 experts with only 37 billion activated parameters per token. Notably, the training cost for DeepSeek-V3 was approximately $5.6 million, a substantial reduction compared to similar models, making it a competitive alternative to proprietary systems like GPT-4 and Claude 3.5 Sonnet. The model is fully open-source and is now available on Hugging Face, reflecting a growing trend in the AI community towards accessible, high-performance models.
View original story
No • 50%
Yes • 50%
10 million • 25%
Other • 25%
1 million • 25%
5 million • 25%
DeepSeek official site • 25%
GitHub • 25%
Other platforms • 25%
HuggingFace • 25%
Between 10% and 30% • 25%
Less than 10% • 25%
Between 30% and 50% • 25%
Greater than 50% • 25%
Three • 25%
More than three • 25%
One • 25%
Two • 25%
11-25% • 25%
26-50% • 25%
51% or more • 25%
0-10% • 25%
2nd Place • 25%
4th Place or lower • 25%
1st Place • 25%
3rd Place • 25%