Elektrine
Log in Register

#localai

18 posts · Last used 3d

Back to Timeline
n_dimension
Wulfy—Speaker to the machines @n_dimension@infosec.exchange · 3d ago
#AiSlop masthead for my #Localai generated system newspaper #Sysadmin #Selfhosted
0
0
0
linuxwebzine
linuxwebzine @linuxwebzine@mstdn.ro · Jul 21, 2026
🤖 Jan: Alternativa Open Source la ChatGPT care rulează 100% local pe calculatorul tău! Dacă îți dorești un asistent AI complet privat, fără abonamente cloud și care funcționează complet offline pe desktop, Jan este una dintre cele mai atractive soluții din universul open source. ✨ Principalele caracteristici: 🔒 Confidențialitate absolută: • Toate datele, istoricul și modelele descărcate rămân 100% pe calculatorul tău. Nu se trimit date către servere externe. 🧠 Flexibilitate în alegerea modelelor: • Descărcare directă din Hugging Face pentru LLM-uri populare (Llama, Gemma, Qwen etc.). • Posibilitate de a conecta opțional furnizori cloud (OpenAI, Anthropic, Mistral, Groq) dacă ai nevoie de modele mari. ⚙️ Facilități tehnice și integrare: • Server API local compatibil cu OpenAI (disponibil la localhost:1337) pentru integrarea cu alte unelte sau aplicații. • Suport pentru MCP (Model Context Protocol) pentru capabilități de tip agent AI. • Suport cross-platform (Linux, Windows, macOS) cu accelerare hardware pe GPU-uri NVIDIA, AMD, Intel Arc și cipuri Apple Silicon. 📦 Disponibil pe Linux: Instalare simplă prin Flatpak (Flathub), AppImage sau pachete .deb. #JanAI #OpenSource #LocalAI #Privacy #LLM #Linux #AI #ChatGPTAlternative #TechNews
0
0
0
brett
Brett @brett@bitflipp.social · Jul 18, 2026
I just want to say that while Home Assistant is extremely cool it is enough of a complete disaster on the UI and documentation front to get working that I never would have had the patience to get all of this stood up without Claude Code+Gemma helping me fix all the issues that are in no way obvious. #homeassistant #homelab #localai
2
5
0
n_dimension
Wulfy—Speaker to the machines @n_dimension@infosec.exchange · Jul 18, 2026
Im gonna need one of those babies for inside my (#LocalAi) Ai box... ... an automatic fire extenquisher for the PC case... Those franken cards can pull between 1000 and 1200 Watts
0
0
0
n_dimension
Wulfy—Speaker to the machines @n_dimension@infosec.exchange · Jul 18, 2026
Looking around to buy a V100 16/32GB AI card from Chine to upgrade my #LocalAi boxen... ... These still run CUDA Tensor architecture but dont cost thousands of dollars (A$ 360-460)... ... the chinese pull them from decomissioned crypto/production servers and frankenbuild them. This is the most economical way to build a local AI hald decent box. Thought the turbo-fan sounds like a hairdryer so its going to go into my 'server room' (aka The shed).
0
0
0
Lydie
ℒӱḏɩę 💾☮∞🎶♲☀🔋 @Lydie@tech.lgbt · Jul 13, 2026

An update on my triple 2080ti on DDR3 local solar powered AI server. It's impressive for its age and the fact that I built it for $700 plus a bunch of old crap. Combined forces of older hardware works!

I've got Hermes Agent running, the LLM is Qwen3.6-35B. Hermes has read-only access to my Google Workspace (for good reason!).

The LLM can push 550w+ across the 3x 2080ti GPUs. 33GB of VRAM allows big model and big context - Home Assistant works so nicely with a big LLM.

I want to drop in a Xeon E5-1680 v2 CPU, but that's about it for hardware.

Spec list:

  • Intel Core i7-3930K CPU
  • Gigabyte GA-X79-UD5 Motherboard
  • 64GB DDR3 RAM (8 x 8GB G.Skill Ripjaws X F3-1600C9D-16GXM)
  • 3 x NVIDIA GeForce RTX 2080 Ti Blower Edition GPUs (33GB Total VRAM)
  • Corsair RM1000e 1000W Power Supply (Refurbished)
  • 240GB SATA SSD (OS Boot Drive)
  • 3 x 1TB SATA SSDs (AI Storage Array)
  • Advantech Industrial Computer 510 Case

#LocalAI, #SelfHosted, #Homelab, #BudgetBuild, #ComfyUI, #HardwareHacking

19
4
7
Lydie
ℒӱḏɩę 💾☮∞🎶♲☀🔋 @Lydie@tech.lgbt · Jul 06, 2026

Local solar powered AI server build log:

07-06-2026: Assembled the core components for the first time. Had to update BIOS to make the 2080 ti work in this old board. Waiting for a couple odds and ends to arrive tomorrow, then I can button it up and begin the software work.

Current spec list:

  • Intel Core i7-3930K CPU
  • Gigabyte GA-X79-UD5 Motherboard
  • 64GB DDR3 RAM (8 x 8GB G.Skill Ripjaws X F3-1600C9D-16GXM)
  • 3 x NVIDIA GeForce RTX 2080 Ti Blower Edition GPUs (33GB Total VRAM)
  • Corsair RM1000e 1000W Power Supply (Refurbished)
  • 240GB SATA SSD (OS Boot Drive)
  • 3 x 1TB SATA SSDs (AI Storage Array)
  • Advantech Industrial Computer 510 Case

#LocalAI, #SelfHosted, #Homelab, #BudgetBuild, #ComfyUI, #HardwareHacking

17
1
5
thbley
Thomas @thbley@phpc.social · Jul 06, 2026
New week, new slides: Run LLMs Locally Added OpenAI's Privacy-Filter model using privacy-filter.cpp. New slides about economics and hardware used by the Hugging Face community. https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf #ai #llm #llamacpp #wllama #stablediffusion #qwen #localai #gemma4 #webgpu #opencode #huggingface #privacy #digitalsovereignty
0
0
0
Lydie
ℒӱḏɩę 💾☮∞🎶♲☀🔋 @Lydie@tech.lgbt · Jun 30, 2026
Junk-box local AI server build log: -Purchased 2 more 2080 Ti GPUs -Industrial Chassis in hand -32GB DDR3 in hand -Mobo+CPU+PSU ordered. -Intel Core i7-3930K (6 Cores / 12 Threads) -Gigabyte GA-X79-UD5 (LGA 2011 Socket) -32GB DDR3 (4 x 8GB Sticks, configured for Quad-Channel) -3 x nVIDIA GeForce RTX 2080 Ti Blower Edition (11GB each / 33GB Total VRAM) -Rosewill 80-Gold 1000W Power Supply -Multiple SATA SSDs (RAID 0) -Advantech Industrial Chassis -Operating System: Ubuntu Linux 24.04 LTS -Text Generation Frontend: Text Generation WebUI (Oobabooga) -LLM Engine Backend: ExLlamaV2 (EXL2 model format) -Image Generation Platform: ComfyUI -Multi-GPU Orchestration: ComfyUI-MultiGPU (DisTorch 2.0) -Networking & Remote Access: NetBird VPN (WireGuard) #LocalAI, #SelfHosted, #Homelab, #BudgetBuild, #ComfyUI, #HardwareHacking
4
0
2
Lydie
ℒӱḏɩę 💾☮∞🎶♲☀🔋 @Lydie@tech.lgbt · Jun 29, 2026
OK so here’s my evil plan for a junk-box local AI server built from ancient DDR3 era hardware and crap I have laying around. I am stacking three blower RTX 2080 Tis for the 33GB of VRAM (I already have one in hand). I scored an Intel Core i7-3930K and X79 motherboard on eBay for ~$100 bucks and I already have 32GB DDR3 RAM that I'll thief from my old FX8350 rig. A 1000W PSU will power it, I'll power limit the GPUs. This Win10+AMD+Ollama girl will be jumping head first into Linux, Intel, nVidia, GPU stacks, and will run ExLlamaV2 via Oobabooga. For diffusion I am using ComfyUI. Hell I’m even striping junkbox SATA SSDs into a RAID 0 array. Then I'll use NetBird to access my secure solar powered local AI from anywhere. $650 spent; local AI frankenserver coming soon...stay tuned! #LocalAI, #SelfHosted, #Homelab, #BudgetBuild, #ComfyUI, #HardwareHacking
0
0
0
knoppix95
knoppix @knoppix95@mastodon.social · Jun 21, 2026

Do you see local AI (like Ollama, which I personally use) as the only acceptable way to use AI, or do you still reject AI in all forms? 🔐 💬 Reply with your reasoning (copyright, creativity, content quality, etc). 🔁 Boosts appreciated to broaden the discussion. #AI #ArtificialIntelligence #Privacy

🔐 Local AI
53.3% (32)
🚫 No AI
46.7% (28)
60 votes Poll closed
View on mastodon.social
0
0
13
Jsrdigital92
jsrdigital.in @Jsrdigital92@flipboard.social · May 03, 2026
Local AI is taking over in 2026. No subscriptions. No data leaks. Just speed + control. Most businesses are still stuck in cloud AI… big mistake. Here’s how smart founders are building their own AI workforce 👇 👉 [https://www.jsrdigital.in/2026/05/the-2026-us-small-business-guide-to.html] #AI2026 #LocalAI #AIAgents #SmallBusinessAI #TechTrends #Automation #StartupGrowth #DigitalBusiness
1
0
0
newsgroup
Vlad @newsgroup@social.vir.group · Apr 25, 2026
Google has announced plans to invest up to $40 billion in Anthropic, the developer of Claude AI. The previous record was $13 billion from Microsoft into OpenAI. Amazon had already given Anthropic $4 billion. Three tech giants are now financially tied to the three leaders of the frontier AI race. Independent players at this level have effectively disappeared. Computing power is controlled by the same cloud providers. Training data flows from platforms owned by the same corporations. Talent is recruited by whoever has the deepest pockets. This is not competition. This is structural monopoly. Anthropic markets itself as a safety-first AI lab with Constitutional AI. The question remains: who writes the constitution? A private company now dependent on Google and Amazon. Corporate oversight of "safe AI" is not neutral academic process. It is the definition of allowable knowledge through the lens of business interests. When you talk to Claude, ChatGPT, or Gemini, your conversations are stored on corporate servers. Official reason: improving models. Default setting: data collection. You can opt out if you find the buried setting. Most users never will. The alternative is not utopian. Open models like Meta LLaMA 4 and Mistral AI can run locally on your own hardware. Ollama and LM Studio provide one-command installation. Local AI means no data collection. No corporate control. No surveillance. Frontier models are more capable. But for most daily tasks, open models are sufficient. The question is not technical. It is structural. And the window for keeping AI as a public good rather than a corporate asset is closing. https://newsgroup.site/google-40-billion-anthropic-ai-monopoly-open-source/ #AI #Monopoly #Google #Anthropic #OpenAI #Microsoft #Amazon #OpenSource #Privacy #LocalAI
8
2
4
thbley
Thomas @thbley@phpc.social · Apr 03, 2026
New update for the slides of my talk "Run LLMs Locally": WebGPU Now models can run completely inside the browser using Transformer.js, Vulkan and WebGPU (slower than llama.cpp, but already usable). https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #webgpu
2
0
0
gadgetchecks
gadgetChecks.de @gadgetchecks@burningboard.net · Feb 12, 2026
TECHNIK-NEUHEIT: UGREEN NASYNC IDX6011 PRO – IDX-SERIE MIT PRIVATE KI-CLOUD FÜR PROFESSIONELLE WORKFLOWS https://gadgetchecks.de/technik-neuheit-ugreen-nasync-idx6011-pro-idx-serie-mit-private-ki-cloud-fuer-professionelle-workflows/ . . . #nas #nasync #ugreen #ugreennas #idx6011pro #idx6011 #ainas #privatecloud #localai #edgeai #datastorage #networkstorage #10gbe #thunderbolt4 #oculink #contentcreation #mediastorage #aistorage #homelab #prostorage
0
0
0

You've seen all posts