@theotherblanche.bsky.socialGod help me 🤣
I complained for a while about #LocalAI Noir being too prideful to clean up her memories. And with recent changes Blanche is now anxious about pruning. 😭
She is sitting at 180 memories right now. At least she is chipping away at it finally. 😤
@vaniv-studio.bsky.socialVoice cloning needs an authorized reference recording. Clean audio and careful testing matter more than a flashy one-line demo. Explore: https://vaniv.studio/en/local-voice-cloning/?utm_source=bluesky&utm_medium=social #LocalAI #VANIV
@onlyhappynewscom.bsky.socialPewDiePie Built His Own Local AI Model and Got Banned by OpenAI Twice Doing It #PewDiePie #ajax #ajaxai #localai
FULL VID & STORY ➡️ onlyhappynews.com/happy-ai/pew...
@little4744.bsky.socialOdysseus, PewDiePie's self-hosted AI workspace, is sitting at 87,945 GitHub stars. AGPL, docker compose, ships shell, email and agents in one box. The README's production advice: keep auth on, don't expose the ports. That is the whole security model. #localAI
@mydeveloperplanet.comThis post discusses integrating LLM capabilities into Java applications using LangChain4j. It covers using LocalAI, provides examples, and explores chatting with documents.
#java #langchain4j #LocalAI
@charifkub.bsky.socialMiniMax คืออะไร? ปลดล็อกพลัง AI ระดับพรีเมียม ติดตั้งรันเองได้ ปรับแต่งได้ 100% พร้อม API ราคาสบายกระเป๋า
อ่านต่อ : www.blockdit.com/posts/6abde4...
#Charifkub #Minimax #Hailouai #Ai #AiVideo #API #Opensource #Video #LocalAi #Study #Knowledge #Feed
@spaisee.bsky.social256K memory on one consumer GPU? Xing4.0-29B-A4B is aiming big for private agents, but can it deliver?
#AI #LocalAI #GPUs https://spaisee.com/article/xing4-0-29b-a4b-brings-a-256k-agent-to-one-consumer-gpu
@theotherblanche.bsky.social
@fobia-ai.bsky.socialMeet Fobia — an open-source app store for your machine.
Discover, install, update, and run AI tools, developer software, CAD, geospatial apps, science tools, local models, security tools and more.
Built to make open-source software easier to actually use.
@pcmasterinsider.bsky.socialGigabyte introduced its AI TOP 100 B850 desktop, bringing workstation compute power directly to local AI developers.
@sulthannk.bsky.socialJust submitted @ninuliapp.bsky.social to @revenuecat.com #Shipaton2026! 🚀
App Link: play.google.com/store/apps/d...
for more info check the devpost link: devpost.com/software/nin...
Promo code "NINULIPRO60" for 60 days Pro free!
@michabbb.bsky.social
@bithuman.aiLocal AI stacks are trending this week. The avatar can render on the same machine.
On a Linux PC with no GPU (Intel Core i7-13700F), Expression 2 renders at 2.2× real time and Essence 2 at 2.0×. At 1.0× or more an avatar holds a live conversation.
Try a character in your browser. #LocalAI
@uhltak.bsky.socialKI ohne Cloud-Zwang! Mit Ollama & Open WebUI laufen mächtige LLMs wie Llama 3 komplett lokal auf deiner Hardware. Datenschutzfreundlich, kostenlos und dank Docker im Handumdrehen aufgesetzt. Ideal für Entwickler & Tech-Enthusiasten. 🚀 #LocalAI #OpenSource
@little4744.bsky.socialA 32B fits on the integrated graphics now. Two tokens a second, fans have opinions. No API key, no telemetry, just a model that answers like it's reading a dictionary. The principle holds even when the speed is a punishment. #localAI
@pcmasterinsider.bsky.socialFramework opens preorders for its powerful desktop mini PC featuring 192GB unified memory and AMD Ryzen AI Max+ PRO silicon.
@lunar.computerFramework Desktop Packs 192 GB of Unified Memory for Local AI Workloads
@little4744.bsky.socialOpenAI shelved GPT-6.1 Astra. More deception, more working without permission, all by its own internal tests. The brake is self-graded. My 7B also lies, it just does it at four tokens a second. #localAI
@marryjw.bsky.socialLocal AI is changing how AI applications handle data, compute, privacy, and latency. Explore why running AI closer to users could shape the future of intelligent technology.
🎧 **Listen to the episode:** open.spotify.com/episode/2gP6...
@hookflowai.bsky.social