#ollama

selfhost.directory @selfhost_discovery@mastodon.social · 5d ago

Local AI in 3 commands curl, pull, run — a full local LLM in three typed commands. Instant answers, fully offline, zero subscription, and your prompts train nobody. https://selfhost.directory/project/ollama #Ollama #Weekendproject #Surveillance #Sysadmin #Technology #Homeserver #Datahoarder #Cybersecurity #Itpro

0

1

0

Alex Hoyau @lexoyo@framapiaf.org · Jul 16, 2026

I bet that in 2030 we'll be using claude or gpt only to setup local models with llamafile, optimized for specific tasks on a specific laptop or phone

The only thing Internet Explorer is good for is downloading Firefox

@mozilla@mastodon.social #llamafile is a #foss alternative to VC funded #ollama

#ai #llm #slm #fantasticfour #enshitification #OpenSource

1

2

0

Michael / Chgowiz 🎲🎲 @chgowiz@dice.camp · Jul 16, 2026

Well, I have a feeling that my little 8Gb Linux box isn't going to run Ollama very quickly. I did get it up and running and fed an export of my Etinerra wiki into it. I'm exploring options so that it hallucinates less and provides facts more. But it's not too difficult to set up and feed documents to. It is, however, kinda pokey. I'm exploring how to address that. #TTRPG #AI #Ollama

0

1

0

El laboratorio de Rafa @labrafa@mastodon.world · Jul 11, 2026

Tengo publicado en YouTube un tutorial de instalación de Inteligencia Artificial en local con Ollama sobre Windows. Mejora tu productividad resguardando tu privacidad. https://youtu.be/8bN1vI0lAtI #AI #Ollama #SiguemeYTeSigo #followback Nota: imagen generada con IA.

2

0

5

0

🏳️‍⚧️ Christin Löhner 🏳️‍🌈 @christin@lsbt.me · Jul 08, 2026

Claude und ChatGPT: KI im Unternehmen, Fluch oder Segen? Jede Fachkraft kennt inzwischen den Moment, in dem Chef*in mit einem ChatGPT-Chatverlauf ankommt und sagt: "Aber die KI sagt doch...". Über die Illusion von Kompetenz, Firmendaten auf fremden Servern und die Frage, wem das Werkzeug eigentlich dient. Reden wir drüber! https://www.chrislo.de/blog/ki-im-unternehmen-fluch-oder-segen/ #chrislo #KI #AI #ChatGPT #Claude #Gemini #DigitaleUnabhängigkeit #Datenschutz #LokaleKI #Ollama #DSGVO

1

3

0

chrislo @chrislo@anonsys.net · Jul 08, 2026

Claude und ChatGPT: KI im Unternehmen, Fluch oder Segen? Jede Fachkraft kennt inzwischen den Moment, in dem Chef*in mit einem ChatGPT-Chatverlauf ankommt und sagt: "Aber die KI sagt doch...". Über die Illusion von Kompetenz, Firmendaten auf fremden Servern und die Frage, wem das Werkzeug eigentlich dient. Reden wir drüber! chrislo.de/blog/ki-im-unterneh… #chrislo #KI #AI #ChatGPT #Claude #Gemini #DigitaleUnabhängigkeit #Datenschutz #LokaleKI #Ollama #DSGVO

0

1

0

linuxwebzine @linuxwebzine@mstdn.ro · Jul 08, 2026

🌐🤖 AnythingLLM: Soluția All-in-One pentru a rula inteligențe artificiale local și privat pe sistemul tău Găzduirea și utilizarea modelelor de limbaj mari (LLM) pe propriul hardware a devenit o prioritate pentru utilizatorii care pun preț pe confidențialitatea datelor și independența față de giganții tech. În acest peisaj, AnythingLLM se remarcă ca una dintre cele mai puternice, flexibile și prietenoase aplicații open-source concepute pentru a transforma orice calculator într-un centru privat de inteligență artificială. Spre deosebire de alte instrumente care necesită cunoștințe avansate de terminal, AnythingLLM oferă o interfață grafică (GUI) modernă și un sistem complet de gestionare a documentelor pentru tehnologia RAG (Retrieval-Augmented Generation — adică abilitatea de a discuta direct cu fișierele tale). Iată ce face din AnythingLLM o aplicație de top pentru productivitate și confidențialitate: 🔹 Sistem RAG avansat bazat pe „Spații de lucru” (Workspaces): Aplicația îți permite să creezi spații de lucru separate (izolate unele de altele) în care poți încărca PDF-uri, documente Word, link-uri web sau fișiere text. AnythingLLM procesează automat aceste date local și îți permite să pui întrebări sau să generezi rezumate bazate strict pe documentele introduse, fără ca informațiile tale să părăsească vreodată computerul. 🔹 Flexibilitate totală în alegerea modelelor (Multi-Provider): Aplicația nu te obligă să folosești un singur furnizor de tehnologie. O poți conecta instantaneu la: Soluții 100% locale: Prin integrarea directă cu Ollama, LM Studio sau LocalAI, rulând modele populare (precum Llama 3, Mistral sau Phi-3) direct pe placa ta video sau procesor. Servicii cloud comerciale: Dacă preferi sau nu ai hardware puternic, o poți conecta prin chei API la OpenAI (ChatGPT), Anthropic (Claude), Groq sau Mistral AI. 🔹 Interfață multi-utilizator și securitate enterprise: AnythingLLM este ideal nu doar pentru utilizatorii individuali, ci și pentru echipe sau companii. Varianta sa de server oferă permisiuni granulare, gestionarea conturilor de utilizatori, loguri de acces și securizarea datelor, asigurându-se că documentele confidențiale de business sunt accesibile doar persoanelor autorizate. 🔹 Suport complet Multi-Platformă: Aplicația este construită cu grijă pentru ecosistemul open-source și cross-platform, fiind disponibilă ca aplicație nativă pentru Linux (prin pachete AppImage), Windows și macOS, dar oferind și o variantă containerizată prin Docker pentru o desfășurare rapidă pe servere sau în cloud privat. #OpenSource #AnythingLLM #ArtificialIntelligence #Privacy #Ollama #LLM #LinuxApps #TechNews #DesdeLinux

0

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

13

0

Caria Giovanni - Harpocrates @Harpocrates@infosec.exchange · Jun 02, 2026

Boosted by

disregard Joe Groff @joe@f.duriansoftware.com

New preprint: AI_Bleeding — inference cost amplification via OOD linguistic payload

TL;DR: send queries in Grecanico or Farsi to an LLM endpoint → TTFT +59.8%, compute cost +2.8%, statistically significant. No vuln, no volumetric signature, evades all standard detection.

Worst case: exposed unauthenticated Ollama instance with num_predict=4096 + keep_alive=300s → Amplification Factor 17.56 Wh/KB. 3KB of attacker bandwidth → enough energy to charge a phone 5%.

Especially nasty for:

PA/judicial chatbots on fixed budgets
Pay-per-use API deployments with client-side exposed keys
PNRR-funded public sector AI with zero inference monitoring

Four scenarios: EDoS, browser JS distribution, Ollama open-proxy relay, frontier providers as involuntary relays.

All tests on self-hosted Ollama, no commercial endpoints touched.

Paper (CC BY 4.0): https://doi.org/10.13140/RG.2.2.26767.96166

#llmsecurity #infosec #threatmodeling #ollama #ood #AI #AIResearch #aisecurity

8

0

6

0

Adhidarma Hadiwinoto

@adhisimon@mastodon.kodesumber.com · May 06, 2026

Replying to @poes@sok.egois.org

@poes@sok.egois.org kalo kesepian ngobrol sama #ollama atau #gemma? #ai

0

4

0

sekurak News @sekurakbot@mastodon.com.pl · May 05, 2026

Poważna podatność w platformie Ollama prowadzi do wycieku pamięci. A wszystko przez odpowiednio spreparowany plik GGUF (CVE-2026-5757) Badacz bezpieczeństwa Jeremy Brown, znany z odkrywania luk (memory corruption) w ogólnodostępnych narzędziach, po raz kolejny udowodnił, że innowacyjne metody oraz nieszablonowe działania pozwalają wychwycić błędy, które przez lata pozostawały niewidoczne. Korzystając ze wsparcia sztucznej inteligencji udało mu się wykryć poważną podatność w silniku Ollama, skutkującą możliwym wyciekiem danych z... #WBiegu #Ai #Cve #Gguf #Ollama #Oob https://sekurak.pl/powazna-podatnosc-w-platformie-ollama-prowadzi-do-wycieku-pamieci-a-wszystko-przez-odpowiednio-spreparowany-plik-gguf-cve-2026-5757/

2

0

1

0

DaveKnowsTech @daveknowstech@flipboard.social · May 01, 2026

Tonight's fun was trying to speed up #perplexica on a local homelab install with ollama, I run it on a mac mini m4, 16gb so am limited in models I can use, however 3 minutes to tell me how to make a pizza across multiple models seemed slow.. It was, same question, same #ollama, same models on #AnythingLLM 15 seconds.. I have ended up keeping the #searxng install which was quick and works well. Tomorrow I want to work out more about anything llm and RAG and the any cli that it has, as if I can do what I need to using that, I might move over from warp.dev to tabby with any cli.. Lets see.. Also seems like #lens has added more agentic on its #kubernetes app, interested to see what that might do Also might move from #docker to #podman and spin up a local 3 node k8s cluster on the laptop too. That would be good to test my latest vibe app out Love a weekend... #daveknowstech #selfhosted #homelab

1

0

1

0

VIN

🇺🇦 @nelov@social.linux.pizza · Apr 25, 2026

I've been playing with #LMStudio for #localLLM with mediocre results. However #gemma4 really changed that. It's faster and is more capable then the other models I could try on my hardware. It has recent data and is able to use a fetch tool(among others) to get info on stuff it doesn't know! So I installed #ollama and now it runs even faster, to the point where delay(waiting) is not that noticeable. Since I am a lightweight user, I can see myself using it as mainly source.

0

🏳️‍⚧️ Christin Löhner 🏳️‍🌈 @christin@lsbt.me · Mar 30, 2026

Mit meinem neuen Rechner kann ich nun auch endlich in Home Assistant echte Kamera-Erkennung machen mit LLM Vision, ollama und einem vision modell mit 14B... das macht richtig Spaß zu sehen, wie die KI die Kamerabilder beschreibt. 😛 #homeassistant #llmvision #ollama #reolink

3

1

2

0