An RTX 3070 used to be a pretty serious GPU.
Then people started running 32B models on their PCs. That's when 8GB of VRAM started becoming a real problem. One setup in this video has an RTX 3070 with 8GB. The owner wanted to run local models with Ollama, including DeepSeek-R1
He's coming, he's coming! Deepseek is here with multimodality!
Deepseek-V4-Flash-Vision-Exp released! API supports three ways to pass in images 1. Base64 encoded image 2. External image URL 3. Reference files uploaded through Files API
Big update to DeepSeek Harness!
Version number: 0.1.1-rc.1 Let's dance tianyi
Deepseek had no issues giving me an in-depth answer when i asked
You have reached the end of the archive
All of deepseek