31.
32.
DiffusionGemma is Google’s fastest AI yet, but it comes with a big trade-off
(androidauthority.com)
33.
34.
DiffusionGemma: 4x Faster Text Generation
(news.ycombinator.com)
35.
The latest Gemma 4 models use a training trick to slash their on-device memory footprint
(androidauthority.com)
36.
Google’s latest on-device AI model is custom-made for your laptop
(androidauthority.com)
37.
38.
39.
40.
Google's new Gemma 4 open AI model is sized for your laptop
(arstechnica.com)
41.
42.
Gemma 4 12B: A unified, encoder-free multimodal model
(news.ycombinator.com)
43.
A 10 year old Xeon is all you need
(news.ycombinator.com)
44.
A 10 year old Xeon is all you need (for 26B-A4B MTP Drafters without GPU)
(news.ycombinator.com)
45.
46.
47.
48.
Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)
(news.ycombinator.com)
49.
Minnesota Becomes First State To Ban Prediction Markets
(slashdot.org)
50.
KV Sharing, MHC, and Compressed Attention
(news.ycombinator.com)
51.
Google’s underrated AI app unlocked 3 amazing on-device AI tools on my Android phone
(androidauthority.com)
52.
53.
A Good Lemma Is Worth a Thousand Theorems (2007)
(news.ycombinator.com)
54.
What's in a GGUF, besides the weights – and what's still missing?
(news.ycombinator.com)
55.
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
(news.ycombinator.com)
56.
Running local models on an M4 with 24GB memory
(news.ycombinator.com)
57.
The Boston library where you still can borrow a giant puppet
(news.ycombinator.com)
58.
The Boston Library Where You Still Can Borrow a Giant Puppet
(news.ycombinator.com)
59.
60.
Today's top topics:
anthropic
chicken scheme
programming language
version 6.0
apple
iphone
jefferies