Hackernews posts about LLaMa3.1

  1. Show HN: Tune LLaMa3.1 on Google Cloud TPUs (github.com)
    189 points by felarof 2 months ago | 52 comments
  2. Longwriter – Increase llama3.1 output to 10k words (github.com)
    154 points by taikon about 2 months ago | 29 comments
  3. Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s (cerebras.ai)
    147 points by campers about 1 month ago | 84 comments
  4. Show HN: Run Llama3.1 405B on a 8GB VRAM challenge [video] (www.youtube.com)
    19 points by lyogavin 4 months ago | 2 comments
  5. Insights from 84,000 comments on "Ask HN: Who Is Hiring" using Llama3.1-70B-FP16 (exxa.notion.site)
    8 points by Blue_Cosma 2 months ago | 1 comments
  6. llama3.1-405B leaked at 3am the day before on 4chan (twitter.com)
    8 points by georgehill 4 months ago | 1 comments
  7. Using Llama3.1 405B to generate political synthetic data (www.oxen.ai)
    5 points by gregschoeninger 4 months ago | 3 comments
  8. Cerebras reaches 1800 tokens/s for 8B Llama3.1 (www.forbes.com)
    4 points by ashvardanian 3 months ago | discuss
  9. CentML gives free access to llama3.1-405B (cserve-llama.centml.com)
    2 points by vvagias 4 months ago | 4 comments
  10. Qwen2.5 Better Than Llama3.1 and GPT4o (8pixlabs.com)
    1 points by gstarwd 2 months ago | 1 comments
  11. Python Chat Using the Substrate API with Llama3.180B and Vector Storage (github.com)
    1 points by kordlessagain 4 months ago | discuss
  12. We fine-tuned Llama 405B on AMD GPUs (publish.obsidian.md)
    495 points by felarof 2 months ago | 101 comments
  13. Show HN: French National Assembly Simulator (assemblee.doesnotexist.club)
    4 points by yassinsiouda 4 months ago | 5 comments
  14. Show HN: Who is hiring job posts count since 2011 (docs.google.com)
    3 points by georgel 3 months ago | 1 comments
  15. Ask HN: Linux-Compat Hardware for Self-Hosted AI Models & gen advice
    1 points by eth0up 3 months ago | discuss