llm

Feeds to Scour
SubscribedAll
Scoured 1975 posts in 9.8 ms

Unsloth Gemma 4 QAT

 🔄Transformer Models
unsloth.ai·

Ollama 0.30 GPU Boost: Faster local Qwen inference on NVIDIA

 🗄️Vector Databases
everylocalai.com··DEV

defai-digital/ax-engine: Apple Silicon LLM runtime supporting Gemma 4 and Qwen 3.6 MTP modes

 🔄Transformer Models  Content type: Code
github.com··Hacker News

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

 🔄Transformer Models  Content type: Academic
arxiv.org·

Google fills out the middle with the Gemma 4 12B

 🤖AI coding
jonpeddie.com·

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

 🔄Transformer Models  Content type: News  Content type: Blog
blog.google··Hacker News

Intelligent inference scheduling with llm-d on Red Hat AI

 🔄Transformer Models
developers.redhat.com·

MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent

 🔄Transformer Models  Content type: Blog
bric.pe.kr··DEV

Google unveils DiffusionGemma, delivering up to 4x faster inference on dedicated GPUs

 🗄️Vector Databases
alternativeto.net·

NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI

 🔄Transformer Models  Content type: Blog
blogs.nvidia.com·

google/gemma-4-12B-it-qat-q4_0-gguf

 🔄Transformer Models
huggingface.co·

DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200

 🔄Transformer Models  Content type: News

What Ollama Reveals About Local AI, Agents, and Open Models

 🤖AI coding  Content type: Blog
odsc.medium.com·

Inferoa AI harness claimed 90% cache savings. We ran it and measured 97.8%

 🤖AI coding

Running LLM Inference on Kubernetes: What It Actually Takes

 🔄Transformer Models  Content type: Blog
fairwinds.com·

Google’s DiffusionGemma is 4x faster than its other Gemma models

 🔄Transformer Models
thenewstack.io·

New comment by alroma90 in "Ask HN: Who wants to be hired? (June 2026)"

 🔍RAG  Content type: Discussion

lightmetal: GPU LLM Inference From a Single Java 25 JAR

 🔄Transformer Models  Content type: Blog
adambien.blog·

The latest Gemma 4 models use a training trick to slash their on-device memory footprint

 🔄Transformer Models
androidauthority.com·

How Gemma Collins’ dad saved her from financial ruin & helped rake in £1.4M last year… he even lives with her & fiancé

 🔍RAG  Content type: News
thesun.co.uk
·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help