CyAI just got the official DeepSeek V4 Flash generating at 130+ tokens/sec on 8 RTX 4090s.
That’s the full, original model – no quantization – running on GPUs anyone can buy. This deployment can now serve fast DeepSeek inference to CyAI. To our knowledge, we’re the first. 👀
5. DeepSeek R1 DeepSeek R1 is a next-level AI chatbot that gives you powerful, smart conversations, all at a lower cost than other models like GPT-4.
It’s fast, efficient, and easy to use.
Testing thinking levels in DeepSeek V4-Flash 0731’s
Same neon Tokyo prompt at off, low, high and max on 2 DGX Sparks
Progress on the agentic newsroom.
Built in my own harness with my daily drivers GLM 5.2 + DeepSeek V4 Flash. It's creating bespoke reports based on what people are actually talking about. It has one job, and uses many tools to do that job in real time. The intent and goal is
You have reached the end of the archive
All of deepseek