2025-12-15
VentureBeat
7 related
Nvidia launches Nemotron 3, a family of AI models using a hybrid mixture-of-experts architecture and the Mamba-Transformer design, in 30B, 100B, and ~500B sizes
Nvidia launched the new version of its frontier models, Nemotron 3, by leaning in on a model architecture that the world's …
2024-07-17
VentureBeat
9 related
Mistral debuts two LLMs: Codestral Mamba 7B, for code generation, based on the Mamba architecture, and Mathstral 7B, for math reasoning and scientific discovery
The well-funded French AI startup Mistral, known for its powerful open source AI models, launched two new entries in its growing family …
2024-03-29
TechCrunch
7 related
AI21 Labs launches Jamba, an AI model that integrates two architectures: transformer and Mamba, which is based on the Structured State Space model
Increasingly, the AI industry is moving toward generative AI models with longer contexts. But models with large context windows tend to be compute-intensive.
Loading articles...