Agnes-AI has released Agnes-3.0-Flash, a 33 billion parameter multimodal model with a 262,144 token context window. The model features a hybrid-attention architecture, combining gated delta-rule recurrent layers with standard global attention layers. It supports text, image, and video understanding, tool calling, and adjustable reasoning effort, making it suitable for demanding tasks. AI
IMPACT This model's hybrid architecture and large context window could push the boundaries for efficient processing of long sequences in multimodal applications.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Read on Hugging Face Trending Models →
- 33B
- Agnes-3.0-Flash
- Agnes-AI/Agnes-3.0-Flash
- Docker
- Google Colab
- Hugging Face
- Kaggle
- lmsysorg
- OpenAI
- SGLang
- transformers
- vLLM
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →