DeepSeek V4.1 Flash negates any hype Navier Stokes generated for OpenAI IPO.
You can use DeepSeek V4.1 Flash for FREE right now 😳
The model is showing up on xplabs: - deepseek-v4.1-flash how to try it: 1. go to 2. find deepseek-v4.1-flash 3. select it and start chatting no need to pay for the models you can try it right now
35B MoE. 8GB of VRAM.
39.3 tokens/s decode. That is Qwen3.6-35B-A3B NVFP4 on a laptop RTX 4060 — not an H100 rack. The hot experts sit in a GPU cache. The rest of the pool lives in system RAM. The paper’s coding-agent run even clears the 33 tok/s Codex median they cite. 🆕
Horse tinder one shot Deepseek V4.1 Flash.
I told it to make a video too and it did!
You have reached the end of the archive
All of deepseek