arrow_back Zurück zu den Freelance-Aufträgen
F

Windows VM ready-to-use (within AI models) for coding

Freelancer

Teilen:
placeIT home_workRemote assignmentBefristet publicAggregierter Job · IT

eventVeröffentlicht am 26. Aug. 2026 · verifiedWir haben am 30. Aug. 2026 bestätigt, dass er noch aktiv ist

€ 30 – € 250 pro Projekt

Über den Job

NO PLACEHOLDERS. Do not insert a placeholder: please read the project details carefully because here are all the details you need to make an accurate estimation. DON’T USE AI to read this announcement: AI switches off your intelligence and makes you miss out on many details that you can only pick up by reading my request carefully. I'm looking for an experienced AI consultant. I need a Windows-based virtual machine that I can use as "AI local web server" (using a web interface like Open WebUI) within models useful for - coding - GUI desing - bugfixing I will NO use it via CLI. See architectural diagram in attached. I’m flexible on the underlying platform—VirtualBox or VMware. Default admin credentials. Mainly I create ASP/VB code and DB (MySql, Access) structure.... but... the virtual machine required must contain only the AI engine and the AI models (+ a web GUI for submitting requests via chat). Nothing else. It's a stand-alone VM. The final VM will have the right models to allow me to use models offline + how to update it. For my IT tasks, i'm using Claude Code (excellent but it has strong limits), OpenCode (but it's a command line tool), Gemini (but is not stronger specialized on coding). I read that is possible to integrate Ollama and Claude Code but I not understand IF Claude Code available (https://docs.ollama.com/integrations/claude-code) is last one or old. I don't know if exists a Deepseek version specialized in coding (I read that DeepSeek V4 Pro is not a good choice). It seems that Claude Sonnet 4.5 is one of right model. Please pay attention on environment performances (probably we could use cloud models). HW available: 16gb RAM and 250gb HD and 2 cores + GPU (I not remember which one) I will accept the assigned job when I am able to use coding models (via browser) to execute develop tasks above WITH NO TOKEN LIMITS. Is it possible to have several local models available, so that the code written by one model can be checked against another model? ----- Budget ----- Please, no ask me «what is your budget for this project?» No upfront. No payment before successful completion of all final test. The proposal must cover the entire project, not just a "minimum viable product" (VMP). Low-low budget available: If you’ve had previous experience, you can certainly reuse a lot of things and so keep your request to a minimum. ----- Milestones ----- The project is a black box: either everything works or nothing works, so it isn’t possible to break it down into milestones A file README on VM desktop is needed to explain how update models installed and how install new online/offline models and/or how to remove models. ----- Collaboration ----- The consulting engagement will commence in August and will be conducted full-remote. Participation in daily update meetings is mandatory and non-negotiable. Failure to adhere to this requirement will result in immediate project disengagement, without exception.

Kostenlos weiterlesen

Erstellen Sie ein kostenloses Konto, um die vollständige Stelle zu sehen und sich zu bewerben.

  • badgePortfolio für Unternehmen sichtbar
  • notificationsAlert bei neuen Jobs per E-Mail
  • favoriteImmer kostenlos, ohne Haken