Open Source LLMs

Feeds to Scour
SubscribedAll
Scoured 233 posts in 5.3 ms

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

 🧠LLMs  Content type: News  Content type: Blog
blog.google··Hacker News

Doubling Qwen3.6-27B on One RTX 3090: ollama llama.cpp + MTP, Lever by Lever (35.7 80.2 tok/s)

 🛠️AI Tooling  Content type: Blog
dev.to··DEV

Neo-X7/Neo-AI: A fully offline AI assistant powered by Ollama. Stores and retrieves conversations using SQLite + LanceDB vector search. No cloud. No API keys. Runs entirely on your machine.

 🛠️AI Tooling  Content type: Code
github.com··DEV

Integrate on-device AI models into your app using Core AI - WWDC26 - Videos

 💡AI

DiffusionGemma: The Developer Guide

 💡AI  Content type: Blog
developers.googleblog.com·

Ask HN: Is it feasible to run a model on device for complete privacy?

 🧠LLMs  Content type: Discussion

Token4Token — pay-per-token inference on Gnosis + Swarm

 🛠️AI Tooling
Less-relevant results

On-device AI is a margin decision

 🛠️AI Tooling  Content type: Blog
ziraph.com··Hacker News

Show HN: Audit any AI/data pairing with Veritrooper

 🧠LLMs

Node.js Annual Releases, Terraform 1.15, Gemma 4 Multimodal

 Vibe Coding  Content type: Discussion
thedevsignal.com··DEV

No Cloud, No Cost: Build an Offline Visual AI Agent with Gemma 4

 🛠️AI Tooling  Content type: Blog
dev.to··DEV

Job Searcher

 💡AI  Content type: Blog
huggingface.co·

Claude Now Writes 80% of Its Own Code — Anthropic's Self-Improvement Milestone Arrives Faster Than Expected

 🔶Claude

Large companies can add a local LLM filter layer to considerably reducing their AI costs

 🧠LLMs

local AI agents for Cursor with pre-tuned marketplace/commu

 🛠️AI Tooling
locaible.com··Hacker News

How I benchmarked a 100% local RAG pipeline to 9/9 (zero API keys)

 📚RAG
buy.polar.sh··DEV

ComfyUI NVFP4 in 2026: 3 Faster Image Generation on RTX 50-Series (and the Right Format for RTX 40-Series)

 💡AI  Content type: Blog
dev.to··DEV

martidu4/honey-ai: 🍯 All-in-one AI honeypot powered by local LLMs. SSH, HTTP, FTP, Telnet, SMTP, MySQL, Redis, Git, VNC, RDP — with canary tokens, tarpits, GZIP bombs, and threat intel reporting.

 🛠️AI Tooling  Content type: Code
github.com··Hacker News

I Could Solve the Problem, but I Could Not Explain It in English. That Is How ExtraBrain Started

 🔶Claude
extrabrain.app··DEV

Purpose-built local AI agents

 ✍️Prompt Engineering  Content type: Blog

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