Hackernews posts about Gemma 3 270

  1. Running a 270M LLM on Android (architecture and benchmarks)
    2 points by ayushranjan99 23 days ago | discuss
  2. Fine-tuning Gemma 3 for mobile (opensource.googleblog.com)
    1 points by nkko 3 days ago | discuss
  3. Gemma 3 270M: Compact model for hyper-efficient AI (developers.googleblog.com)
    824 points by meetpateltech 4 months ago | 317 comments
  4. Gemma 3 270M re-implemented in pure PyTorch for local tinkering (github.com)
    417 points by ModelForge 4 months ago | 57 comments
  5. Own your AI: Learn how to fine-tune Gemma 3 270M and run it on-device (developers.googleblog.com)
    5 points by simonpure 2 months ago | discuss
  6. Gemma 3-270M (huggingface.co)
    4 points by georgehill 4 months ago | discuss
  7. You can fine-tune Gemma3-270M and prepare for secure deployment within minutes (www.youtube.com)
    3 points by astro_09 4 months ago | discuss
  8. Gemma 3 270M – Google's NEW AI – How to Fin-tune Gemma3 [video] (www.youtube.com)
    2 points by rjn32s 4 months ago | 1 comments
  9. Tiny gemma3 270M implementation in R (github.com)
    2 points by dfalbel 4 months ago | discuss
  10. Gemma 3 270M (twitter.com)
    2 points by tosh 4 months ago | discuss
  11. Launch HN: Cactus (YC S25) – AI inference on smartphones (github.com)
    123 points by HenryNdubuaku 3 months ago | 63 comments
  12. Show HN: AfriTales – Discover the Magic of African Storytelling (afritales.org)
    42 points by ggap 4 months ago | 26 comments
  13. Show HN: Nabu (TTS Reader and LLM Playground on Android) (github.com)
    7 points by mewmix 4 months ago | discuss
  14. Gemma 3 QAT Models (simonwillison.net)
    4 points by mdp2021 8 months ago | 3 comments
  15. Google's Gemma 3 is an open source, multimodal single-GPU AI 128K context window (arstechnica.com)
    4 points by danboarder 9 months ago | 1 comments
  16. Show HN: Local LLM Notepad – run a GPT-style model from a USB stick (github.com)
    40 points by davidye324 6 months ago | 9 comments
  17. Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts (bilawal.net)
    31 points by phantompeace 4 months ago | 8 comments
  18. Show HN: Chromem-go – Embeddable vector database for Go (github.com)
    3 points by PhilippGille over 1 year ago | 2 comments
  19. Presentation Decks are a lot easier to create with Gamma
    40 points by FutureStacked_ 3 months ago | 2 comments
  20. Ask HN: Residue Number Systems for GPU computing as indie-researcher. Thoughts?
    1 points by muragekibicho 7 months ago | discuss