With 17B active parameters, but within a larger 400B total, employing 128 experts in its MoE architecture.

Features 17B active parameters within a 109B total, utilizing 16 experts in a Mixture-of-Experts (MoE) architecture. ​

Experience the enhanced capabilities of DeepSeek-V3-0324 today and explore its potential in your projects and daily tasks.

Qwen 32B is a powerful 32-billion-parameter large language model developed by Alibaba Cloud, designed for diverse AI applications.

DeepSeek-R1-Distill-Llama-70B is a high-performance, reasoning-focused AI model optimized for efficiency and advanced problem-solving.

A multilingual, efficient, and powerful AI model tailored for advanced instruction-following and versatile tasks.

Low latency LLM which prioritizes speed and efficiency. The perfect choice for retrieval and quick response tasks