Loading activity…
@zizhpan
Researcher @deepseek_ai. Words are my own.
AI
DeepSeek's README offers offline inference for DeepSeek-V4.1-Flash but lists additional systems needed for a complete service.
Technology
The company says the model improves benchmarks, task speed and output length over its predecessor.
AI
DeepSeek says the model is live on its website, app and API, and optimized for DeepSeekHarness and Tencent CodeBuddy.
AI
One viewer says the results exceeded expectations; another praises them but calls V4.1 far from the best vision-language model.
Technology
DeepSeek says its KV cache, which lets the model reuse earlier calculations, needs a quarter of the high-bandwidth memory and an eighth of the SSD storage required by the previous generation's cache.
AI
DeepSeek states its new experimental model adds vision to the V4-Flash API along with a Files API for image reuse.
