AI · 2h ago
LongCat-2.0: 1.6T Parameter MoE Model Released
LongCat-2.0 is a mixture-of-experts model with 1.6 trillion total parameters and 48 billion active per token. The open-source release targets efficient large-scale AI inference. It claims competitive performance with reduced computational cost.
Meridian48 take
The active parameter count is modest, but the total parameter count raises questions about practical deployment and memory requirements.
Read the full reporting
LongCat-2.0, a large-scale MoE model with 1.6T total and 48B Active →
Hacker News
mixture-of-expertslarge-language-model