Hackernews posts about Gemma

1. Google releases Gemma 4 open models (deepmind.google)
   1806 points by jeffmcjunkin 5 days ago | 473 comments
2. Gemma 4 on iPhone (apps.apple.com)
   851 points by janandonly 2 days ago | 232 comments
3. Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code (ai.georgeliu.com)
   401 points by vbtechguy 2 days ago | 98 comments
4. April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini (gist.github.com)
   322 points by greenstevester 4 days ago | 119 comments
5. Show HN: Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B (github.com)
   276 points by karimf 2 days ago | 35 comments
6. Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud (github.com)
   152 points by ikessler 1 day ago | 21 comments
7. Gemma Needs Help (www.lesswrong.com)
   38 points by pr337h4m 27 days ago | 1 comments
8. Gemma 4: Byte for byte, the most capable open models (blog.google)
   24 points by meetpateltech 5 days ago | 2 comments
9. Gemma 4 running client-side in WebGPU (huggingface.co)
   8 points by astlouis44 3 days ago | discuss
10. Gemma 4 Uncensored (autoresearch results) (huggingface.co)
    5 points by adefa 2 days ago | 4 comments
11. Gemma 4 Models (huggingface.co)
    5 points by maciejgryka 5 days ago | 1 comments
12. A Visual Guide to Gemma 4 (newsletter.maartengrootendorst.com)
    4 points by mariuz 4 days ago | 1 comments
13. Run Gemma 4 in Your Browser (huggingface.co)
    4 points by oldfuture 1 day ago | discuss
14. Gemma 4 makes local AI agents practical (firethering.com)
    4 points by steveharing1 4 days ago | discuss
15. Gemma 4 running on NVIDIA and AMD from Day 0 with MAX (www.modular.com)
    4 points by sparklychipmunk 5 days ago | discuss
16. ‎PocketPal AI App. Run Gemma 4 and other hugging faces models on device (apps.apple.com)
    3 points by janandonly about 3 hours ago | discuss
17. Fine-tuning Gemma 4 locally
    3 points by logicallee 1 day ago | discuss
18. Local LLM for OpenCode Gemma 4 26B A4B. No GPU required (grigio.org)
    3 points by grigio 3 days ago | discuss
19. Running Qwen 35B on 16GB Mac Mini via MMAP (17 tok/s) then swapping to Gemma 4 (thoughts.jock.pl)
    3 points by joozio 4 days ago | discuss
20. Gemma 4 reports, configs, and code, here are the takeaways (twitter.com)
    3 points by tzury 5 days ago | discuss
21. Gemma 4 running locally in the browser with transformers.js (huggingface.co)
    3 points by clmnt 5 days ago | discuss
22. Gemma 4 Model Card (ai.google.dev)
    3 points by Topfi 5 days ago | discuss
23. Selectively reducing eval awareness and murder in Gemma 3 27B via steering (www.lesswrong.com)
    3 points by gmays 26 days ago | discuss
24. Gemma 4: The new standard for local agentic intelligence on Android (android-developers.googleblog.com)
    2 points by xnx 5 days ago | 1 comments
25. Google AI Edge Eloquent is a Gemma-powered dictation app that works offline (www.neowin.net)
    2 points by bundie about 8 hours ago | discuss
26. Gemma 4 clocking 12 tokens / SEC on Pixel 7A (twitter.com)
    2 points by amrrs about 16 hours ago | discuss
27. Welcome Gemma 4: Frontier multimodal intelligence on device (huggingface.co)
    2 points by ibobev about 23 hours ago | discuss
28. Google's Gemma 4 is good, but you won't use it (www.riteshkhanna.com)
    2 points by treadon 4 days ago | discuss
29. Google battles Chinese open-weights models with Gemma 4 (www.theregister.com)
    2 points by Brajeshwar 4 days ago | discuss
30. AICore Developer Preview Supports Gemma 4 on Pixel TPUs (android-developers.googleblog.com)
    2 points by spijdar 5 days ago | discuss