Local AI

Feeds to Scour
SubscribedAll
Scoured 164 posts in 6.0 ms

Open-LLM-VTuber Review: Offline AI Companion with Live2D

 💾ARM  Content type: Blog
dev.to··DEV

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

 AI Hardware
androidauthority.com·

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 Automation  Content type: Code
github.com··DEV

I stopped fighting LM Studio's model UI and switched to Ollama — setup took minutes instead of hours

 ⚙️LLM Fine-tuning
makeuseof.com·

Get this Alexa+ premium feature for free in Home Assistant

 📡Zigbee
howtogeek.com·

Running Ollama on a 15W CPU sounded ridiculous until I got it working with decent results

 🖥️Self-Hosting
xda-developers.com·

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

 🔍RAG
buy.polar.sh··DEV

Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn’t Be This Good

 AI Hardware  Content type: Blog
towardsai.net·
Less-relevant results

How to Fine-Tune an SLM for Emotion Recognition

 ⚙️LLM Fine-tuning

Lenovo ThinkStation PGX review: I may have just found the best mini workstation for OpenClaw, and it’s not a Mac mini

 💻Laptops
techradar.com
·

The smartest ChatGPT users are putting local AI in front of it — here's why

 ✍️Prompt Engineering
tomsguide.com
·

I switched from LM Studio to llama.cpp, and I'm never going back to a bloated wrapper

 🌐Open Source
howtogeek.com·

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

 🏠Home Assistant  Content type: Blog
dev.to··DEV

I got a Crush on this new Terminal-based AI coding tool

 🔌APIs
xda-developers.com·

Google’s latest on-device AI model is custom-made for your laptop

 🤖Android
androidauthority.com·

My First $5,000 Month Writing About AI Engineering on Medium

 🤖AI Agents  Content type: Blog
towardsai.net·

shoo99/paper-rag: A private, fully-local RAG over your own PDFs: BGE-M3 + embedded Qdrant + a local LLM via Ollama. ~150 lines, nothing leaves your machine.

 🔍RAG  Content type: Code
github.com··DEV

This cloud workspace gives your laptop the GPU it never had

 🤖AI Agents
makeuseof.com·

I used ChatGPT and Gemini side-by-side for a month on Android, and only one behaved like a senior AI tool

 🤖Android
androidpolice.com·

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

 AI Hardware  Content type: Blog
dev.to··DEV

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