Models⚡
DeepSeek V4.1 Flash
DeepSeek's MoE model with 552B total parameters and 8-16B active per token. 1M-token context, MIT license: free commercial use. Built for online serving, too large for local use on a single PC.
LLMDeepSeekMoEOpen Source
Back to resources
Organizations💚
DeepSeek
DeepSeek (Hangzhou, China): founded in 2023 as a division of the brokerage High-Flyer, with ~200 employees it builds the most efficient open-weight LLMs in their class, focused on low-activation MoE. DeepSeek V4.1-Flash pushes 552B total parameters with ~8B active and a 1M context. The models in the catalog are the child resources.
Features
- V4.1-Flash: 552B total / 8B active (MoE)
- Context up to 1M tokens
- Consumer-hardware inference thanks to few active parameters
Technical specifications
- Headquarters
- Hangzhou (China)
- Founded
- 2023
- Employees
- ~200
- Revenue
- Not disclosed
- Ownership
- Private company (a division of High-Flyer)
Resources by DeepSeek
Tags
Discover DeepSeek
Visit the official site to download, learn more and start using DeepSeek.