Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • What are the usecase that you can think of because 3.77 tok/s is actually to slow and better call a cloud API to do the task
  • looks promising, will test it out.
  • also, can it work as AI agent for coding as well?
  • Read the readme but still unclear - does this mean we can run DeepSeek v4.1 Flash on GPUs with 8GB VRAM?
  • how to test it? and, will it be unlimited free? well, I am using a laptop, which is a 2010 model, but has 8gb ram. Ram is well but the processor is from straight 16 years ago, 1st generation CPU!

Explore Birbla archives