Hackernews posts about Llama 3

Llama 3 is an AI-powered chatbot that uses pure NumPy to generate human-like conversations in a browser-based interface.

1. Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts (bilawal.net)
   31 points by phantompeace 16 days ago | 8 comments
2. Load Llama-3.2 WebGPU in the browser from a local folder (simonwillison.net)
   3 points by indigodaddy 9 days ago | discuss
3. Show HN: I built an AI that roasts your website and gives tips to fix it (ai-roast-vert.vercel.app)
   7 points by happy_malone 5 days ago | 4 comments
4. Show HN: VeritasGraph,An on-premise Graph RAG with verifiable source attribution (github.com)
   3 points by Bibinprathap 10 days ago | 1 comments
5. LLM Inference Providers – Recommendations?
   1 points by ane-multiverse 1 day ago | discuss
6. Show HN: Aotol AI – Offline LLM app runs on iOS with voice and multilingual (apps.apple.com)
   1 points by doublez78 3 days ago | discuss
7. Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5 (github.com)
   347 points by b4rtazz 11 days ago | 161 comments
8. Show HN: Lemonade: Run LLMs Locally with GPU and NPU Acceleration (github.com)
   15 points by ramkrishna2910 29 days ago | discuss
9. I'm happy with Bluesky but what happened to Threads (and also "x"?)
   5 points by adinhitlore 24 days ago | 1 comments
10. Ask HN: What in your opinion is the best model for vibecoding? My thoughts below
    1 points by adinhitlore 1 day ago | 2 comments
11. Show HN: Mixture of Voices–Open source goal-based AI router-uses BGE transformer
    1 points by KylieM about 5 hours ago | 1 comments
12. A Python RAG tutorial with Pinecone and Ollama 3.2 with a code example (blog.yasuflores.me)
    2 points by carlosyasu91 30 days ago | discuss
13. Show HN: Llmswap v3.0 – CLI and SDK for OpenAI, Claude, Gemini, Watsonx (pypi.org)
    2 points by sreenathmenon 28 days ago | discuss
14. Ollama and Bifrost –> Qwen3 in Claude Code
    1 points by all2 13 days ago | 2 comments
15. What is the minimum hardware to run 671B DeepSeek 3.1
    2 points by roscas 22 days ago | 3 comments
16. Show HN: Pluely v0.1.3 – Invisible Open Source AI Assistant with System Audio (pluely.com)
    2 points by truly_sn 9 days ago | discuss
17. Show HN: BrowserOS -- browser agents with GPT-OSS, local llms (github.com)
    12 points by felarof 26 days ago | 2 comments
18. Show HN: Pantheon-CLI – Open-Source Python Claude Code and Smart Notebook (github.com)
    6 points by steorra 22 days ago | 7 comments
19. Ask HN: Why aren't local LLMs used as widely as we expected?
    5 points by briansun 9 days ago | 10 comments
20. Show HN: Llmswap – Universal AI SDK and Code Generation CLI (sreenathmenon.com)
    5 points by sreenathmenon 7 days ago | discuss
21. Show HN: Dr. WFGY – an AI doctor for broken pipelines (chat-based） (chatgpt.com)
    3 points by tgrrr9111 11 days ago | 2 comments
22. Show HN: AionUi v1.2 – GUI to Boost Gemini CLI with Multi-Agent (github.com)
    1 points by waili 6 days ago | discuss
23. Show HN: Per row context understanding for data transformations (github.com)
    1 points by abhijithneil 13 days ago | discuss
24. Meta Llama 3 (llama.meta.com)
    2199 points by bratao over 1 year ago | 923 comments
25. Llama3 implemented from scratch (github.com)
    1041 points by Hadi7546 over 1 year ago | 269 comments
26. Llama 3.2: Revolutionizing edge AI and vision with open, customizable models (ai.meta.com)
    924 points by nmwnmw 12 months ago | 328 comments
27. Show HN: Llama 3.2 Interpretability with Sparse Autoencoders (github.com)
    579 points by PaulPauls 10 months ago | 99 comments
28. Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPU (github.com)
    547 points by abi over 1 year ago | 139 comments
29. Llama 3 implemented in pure NumPy (docs.likejazz.com)
    476 points by orixilus over 1 year ago | 50 comments
30. Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars (aksh-garg.medium.com)
    459 points by minimaxir over 1 year ago | 77 comments
31. Llama 3.1 (llama.meta.com)
    437 points by luiscosio about 1 year ago | 269 comments
32. Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference (cerebras.ai)
    427 points by benchmarkist 10 months ago | 156 comments
33. Llama-3.3-70B-Instruct (huggingface.co)
    425 points by pr337h4m 10 months ago | 219 comments
34. g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains (github.com)
    334 points by gfortaine about 1 year ago | 148 comments
35. Llama 3.1 Omni Model (github.com)
    304 points by taikon 12 months ago | 41 comments
36. Cost of self hosting Llama-3 8B-Instruct (blog.lytix.co)
    245 points by veryrealsid over 1 year ago | 183 comments
37. DeepDive in everything of Llama3: revealing detailed insights and implementation (github.com)
    222 points by therealoliver 7 months ago | 14 comments
38. I Self-Hosted Llama 3.2 with Coolify on My Home Server (geek.sg)
    221 points by whitefables 11 months ago | 90 comments
39. llama-fs: A self-organizing file system with llama 3 (github.com)
    221 points by archb over 1 year ago | 62 comments
40. Llama 3.1 in C (github.com)
    212 points by AMICABoard about 1 year ago | 36 comments
41. Run llama3 locally with 1M token context (ollama.com)
    204 points by mritchie712 over 1 year ago | 72 comments
42. Show HN: Llama 3.3 70B Sparse Autoencoders with API access (www.goodfire.ai)
    201 points by trq_ 9 months ago | 51 comments
43. Ollama v0.1.33 with Llama 3, Phi 3, and Qwen 110B (github.com)
    192 points by ashvardanian over 1 year ago | 64 comments
44. Meta's Llama 3.1 can recall 42 percent of the first Harry Potter book (www.understandingai.org)
    191 points by aspenmayer 3 months ago | 305 comments
45. Show HN: Tune LLaMa3.1 on Google Cloud TPUs (github.com)
    189 points by felarof about 1 year ago | 52 comments
46. Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally (ollama.com)
    182 points by BUFU 11 months ago | 25 comments
47. Llama 3 8B is almost as good as Wizard 2 8x22B (huggingface.co)
    168 points by tosh over 1 year ago | 111 comments
48. Implementing LLaMA3 in 100 Lines of Pure Jax (saurabhalone.com)
    167 points by jxmorris12 7 months ago | 22 comments
49. Longwriter – Increase llama3.1 output to 10k words (github.com)
    154 points by taikon 12 months ago | 29 comments
50. Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s (cerebras.ai)
    147 points by campers 11 months ago | 84 comments
51. Hermes 3: The First Fine-Tuned Llama 3.1 405B Model (lambdalabs.com)
    146 points by mkaic about 1 year ago | 67 comments
52. Fine tune LLAMA3 on million scale dataset in consumer GPU using QLora, DeepSpeed (medium.com)
    145 points by mehulashah over 1 year ago | 26 comments
53. Llama 3 feels significantly less censored than its predecessor (ollama.com)
    123 points by davidbarker over 1 year ago | 39 comments