Hackernews posts about Llama3

Llama3 is an AI language model that was implemented from scratch and can be used for tasks such as text generation, translation, and question-answering.

1. I Self-Hosted Llama 3.2 with Coolify on My Home Server (geek.sg)
   221 points by whitefables 25 days ago | 90 comments
2. Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally (ollama.com)
   182 points by BUFU 3 days ago | 24 comments
3. Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s (cerebras.ai)
   147 points by campers 16 days ago | 84 comments
4. HuggingFace - Tencent launches Hunyuan Large which outperforms Llama 3.1 405B (huggingface.co)
   23 points by janik-io 4 days ago | 1 comments
5. Nvidia releases weights for Llama-3.1-Nemotron-70B-Instruct (huggingface.co)
   9 points by rvnx 24 days ago | 3 comments
6. Nvidia Llama-3.1-Nemotron-70B-Instruct (build.nvidia.com)
   9 points by KenHV 24 days ago | discuss
7. Scaling Automatic Neuron Description (Describing Every Neuron in Llama 3) (transluce.org)
   8 points by ekzhang 17 days ago | 1 comments
8. Llama 3.1 Nemotron 70B: Open model closing the gap with GPT-4o and Sonnet-3.5 (huggingface.co)
   7 points by victormustar 25 days ago | discuss
9. Cerebras runs Llama 3.1 70B at 2,100 tokens per second, live demo available (twitter.com)
   6 points by modeless 16 days ago | discuss
10. Cerebras Inference now runs Llama 3.1-70B at 2100 tokens/s (cerebras.ai)
    6 points by cs-fan-101 16 days ago | discuss
11. Llama3.2-Vision on Ollama (ollama.com)
    2 points by taran_narat 2 days ago | discuss
12. Llama-3.1-Nemotron-70B-Instruct Model (build.nvidia.com)
    2 points by lapnect 18 days ago | discuss
13. Best Open Source LLM:Tencent Hunyuan-Large Outperforming Llama 3 and DeepSeek V2 (techwavearena.com)
    1 points by tiime 2 days ago | discuss
14. On Device Llama 3.1 with Core ML (machinelearning.apple.com)
    1 points by 2bit 8 days ago | discuss
15. How to Run Meta Llama 3.1 405B with Nebius AI Studio API (nebius.com)
    1 points by dsaed 12 days ago | discuss
16. Quickly accessing llama3.2 from a terminal (or any other model) (disobey.dev)
    1 points by aaaljaz 22 days ago | discuss
17. Ask HN: Local RAG with private knowledge base
    108 points by zephodb 13 days ago | 40 comments
18. Show HN: Mixlayer – code and deploy LLM prompts using JavaScript (www.mixlayer.com)
    5 points by zackangelo 29 days ago | discuss
19. Show HN: How to guide on training Llama-405B using PyTorch distributed APIs (github.com)
    3 points by lambda-research 26 days ago | 4 comments
20. Is it just me or are LLM chat bots still useless in many cases?
    3 points by pthr 26 days ago | 2 comments
21. Ask HN: AI Cloud Computing, is it cheaper than the OpenAI API in the end?
    2 points by calipsow 17 days ago | 4 comments
22. Show HN: I built an AI bank statement converter saves 20hrs/week on data entry (bankstatementconvert.com)
    2 points by Alan_Swift 1 day ago | discuss
23. Show HN: Open-Source Alternative for GitHub Copilot (marketplace.visualstudio.com)
    1 points by suneelak 7 days ago | 4 comments
24. Show HN: Senti – Offline LLM Voice Chat (testflight.apple.com)
    1 points by syousif 10 days ago | 1 comments
25. Show HN: Most Efficient Batch API for Open-Source and Custom Models (withexxa.com)
    1 points by Blue_Cosma 23 days ago | discuss
26. Llama 405B 506 tokens/second on an H200 (developer.nvidia.com)
    21 points by moondistance 27 days ago | 5 comments
27. Open-source 70B model surpass GPT-4o and Claude 3.5 on Arena Hard (huggingface.co)
    8 points by openbuilder 25 days ago | discuss
28. Nvidia Nemotron (huggingface.co)
    2 points by vincent_s 24 days ago | discuss
29. Fine-Tuning LLMs to Resist Indirect Prompt Injection Attacks (labs.withsecure.com)
    1 points by sunbum 20 days ago | discuss
30. Quantized Llama models with increased speed and a reduced memory footprint (ai.meta.com)
    508 points by egnehots 16 days ago | 122 comments