Hackernews posts about Llama 3.2 3B

1. 01
   

   newShow HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcriptsbilawal.net

   ▲ 31phantompeace431d💬 8savesaved
2. 02
   

   newShow HN: Llama 3.2 3B and Keiro Research achieves 85% on SimpleQAwww.keirolabs.cloud

   ▲ 6mannybruv245d💬 1savesaved
3. 03
   

   newRun Llama 3.2 3B on your phoneapps.apple.com

   ▲ 3tiharz657d💬 1savesaved
4. 04
   

   newRunning Llama 3.2 (3B) locally on iPhone Protwitter.com

   ▲ 2aghilmort696ddiscusssavesaved
5. 05
   

   newShow HN: Knowledge graph of restaurants and chefs, built using LLMstheophilecantelob.re

   ▲ 201theophilec613d💬 39savesaved
6. 06
   

   newShow HN: Narada – Open-source secrets classification model

   ▲ 6sanketsaurav389d💬 2savesaved
7. 07
   

   newShow HN: LLMKube – Kubernetes for Local LLMs with GPU Accelerationgithub.com

   ▲ 5defilan353ddiscusssavesaved
8. 08
   

   newShow HN: Focu, open-source mindful productivity app for macOSgithub.com

   ▲ 5martin-buur635ddiscusssavesaved
9. 09
   

   newShow HN: Run 30B model in 4GB Active Memorygithub.com

   ▲ 4vkkhare519d💬 2savesaved
10. 10
    

    newShow HN: Got Tired of LLMs refusing to visit URLs Built open source analyzer CLIgithub.com

    ▲ 3thetall0ne317d💬 3savesaved
11. 11
    

    newShow HN: A book that builds GPT-2, Llama 3, DeepSeek from scratch in PyTorch

    ▲ 2s1lv3rj1nx205d💬 1savesaved
12. 12
    

    newShow HN: QueryVeil – An AI data analyst that investigates your datawww.queryveil.com

    ▲ 2david-rodriguez255ddiscusssavesaved
13. 13
    

    newShow HN: Distil expenses – personal finance agentgithub.com

    ▲ 2gabika368ddiscusssavesaved
14. 14
    

    newShow HN: Benchmarking the Keep memory system with LoCoMokeepnotes.ai

    ▲ 1inguz249ddiscusssavesaved
15. 15
    

    newShow HN: Aotol AI – Offline LLM app runs on iOS with voice and multilingualapps.apple.com

    ▲ 1doublez78418ddiscusssavesaved
16. 16
    

    newShow HN: Off Grid: On-device AI-web browsing, tools vision,image,voice–3x faster

    ▲ 12ali_chherawalla255d💬 5savesaved
17. 17
    

    newShow HN: OfflineLLM: Live Voice Chat with DeepSeek, Llama on iOS and VisionOSofflinellm.bilaal.co.uk

    ▲ 4bilaal_dc5631523d💬 2savesaved
18. 18
    

    newShow HN: I built a <400ms latency voice agent that runs on a 4gb vram GTX 1650"github.com

    ▲ 2shubham-coder272d💬 1savesaved
19. 19
    

    newOff Grid: On-device AI-web browsing, tools, vision, image gen, voice – 3x faster

    ▲ 1ali_chherawalla255d💬 1savesaved
20. 20
    

    newShow HN: We Gave an LLM Adventure Engine a Body, Now It Feels Exhaustedmycelialmirror.medium.com

    ▲ 1oopismcgoopis255ddiscusssavesaved

· edit