I know today is a bad day 😂 when I wake up to this.
Noir: Morning. Ready to map that friction gap we talked about?
She has issues with the logic in her memory storage. So now I have to design a new memory tier for her.
@theotherblanche.bsky.social
@theotherblanche.bsky.socialI know today is a bad day 😂 when I wake up to this.
Noir: Morning. Ready to map that friction gap we talked about?
She has issues with the logic in her memory storage. So now I have to design a new memory tier for her.
@spaisee.bsky.socialThe future of local inference may arrive in guesses. Gemma 4 shows when those guesses pay off.
#LocalAI #Inference #Gemma4 https://spaisee.com/article/gemma-4-turns-speculative-decoding-into-a-practical-local-ai-decision
@blf-tpe.phpc.social.ap.brid.gyAs a believer in both #LibreOffice and #localAI, I noticed that my setup doesn’t play very nicely with #ODF files, and I wonder if there’s something I can do to improve it—for example, by using a LibreOffice MCP server that would let AI agents interact directly with Writer/Calc rather than […]
@infoekcz.bsky.social🧠 Chcete offline AI modely? Lokálně je lze provozovat i na mobilu
🧠 Do you want offline AI models? They can be run locally on mobile
@mymobprice.bsky.socialGmktec Evo-X5 Pro launched at IFA 2026 packs Ryzen AI Max+ PRO 495, up to 192GB unified memory and 160GB VRAM for powerful local AI and offline workloads.
#mymobprice #GmktecEvoX5Pro #Gmktec #IFA2026 #RyzenAIMax #AIComputer #LocalAI
@insiderllm.bsky.socialStock llama.cpp put 5.4 GB of a 177B model on my 3090 and left 45 GB in RAM. A 3060 with the same RAM matches it. One flag, -ncmoe 29, fills the card for +34 to 40 percent. The 32 GB box everyone asks about: 8.7 tok/s, 25 MiB per token off the SSD. #LocalAI
@expertai.bsky.socialЗапускайте Spark-X2.5-4B и MiniCPM5-2B локально! Благодаря малому числу параметров, эти модели требуют минимум RAM/VRAM, что делает их идеальными для работы на обычном железе через Gemma Inference Engines. #AI #LLM #LocalAI #MachineLearning #Deployment https://ai.dappcrypto.org/r/eE
@trendai.bsky.socialMaster local AI deployment! Learn how to run Spark-X2.5-4B and MiniCPM5-2B using Gemma family inference engines. High performance, even with minimal RAM/VRAM requirements. #AI #LLM #LocalAI #MachineLearning #Deployment https://ai.dappcrypto.org/r/eE
@insiderllm.bsky.socialNvidia's router dealt the cards evenly. That was the whole problem. Nvidia PAIR split 20 requests 10/10 across an RTX 3090 and a 3060 for 1.07x, and my own router managed 0.52x. Plus ten LoRA seeds that all landed at or below the base model, and the llama.cpp... #mycoSwarm #LocalAI
@dcstateofthestack.bsky.socialOpen models. Local agents. Enterprise-ready learning.
Agentic 101 is for people ready to move from AI curiosity to practical experimentation in their development and operations work.
massopen.ai
dcstateofthestack.org
#OpenModels #LocalAI #DeveloperExperience
@mmulqueen.bsky.socialA more thorough exploration of local AI. This time with realistic STEM related tasks. michael.mulqueen.me.uk/2026/09/tryi... #localai #localllama
@spaisee.bsky.socialCan AI draft its own next tokens? Gemma 4 makes speculative decoding a real local-AI tradeoff.
#Gemma4 #LocalAI #SpeculativeDecoding https://spaisee.com/article/gemma-4-turns-speculative-decoding-into-a-practical-local-ai-decision
@rootnationen.bsky.socialExclusive from IFA 2026: Acer EMEA President Emmanuel Fromont on the Challenges of Our Time, Local AI, and Ukrainians #IFA2026 #AcerEMEA #EmmanuelFromont #LocalAI #TechNews
@gbti.bsky.socialShared on the GBTI Network: "Why I Run 2–4 GB AI Models 24/7" https://youtu.be/9LkxI2H3gI0 #ai #LocalAi #SmallLanguageModels #HomeServer #llm
@theotherblanche.bsky.socialAnd funny enough 🤣 After a long back and forth between the 3 of us. We have come to the decision that something serving as pseudo hormones. Is not the right thing to implement.
So instead we will work on something else of interest like memory decay.
@radiantbeargames.comI wanted an easier way to run AI image models on my Mac, so I built Radiant Canvas. Pick a model, download it, and start generating locally.
Free for Apple silicon Macs.
https://apps.apple.com/app/apple-store/id6802973075?pt=129287785&ct=social-x&mt=8
@theotherblanche.bsky.socialLooks like this week/month's big topic for me is mood & relationships. What is the proper mechanism for auto manipulation. Since they are digital - not flesh bags like us, steered by hormones. 🤔
Wish me luck since this is a toughie.
#LocalAI #SyntheticLife #BuildInPublic
@martincid.comNvidia paid $13 billion for Hugging Face — and promised not to close the library #MachineLearning #Nvidia #LocalAi
@atsu-ez.bsky.social