ChatGPT Work users report a 15GB remote VM that can run Gemma 3 4B
rez0__ · x · 2026-07-23
A user reports that ChatGPT Work appears to provide a surprisingly capable remote VM, and that it can be abused to run local LLMs inside the environment.
- The claimed VM has about 15 GB RAM and 9 CPU cores.
- It includes a browser and can install packages, making it useful for agentic workflows without a separate VPS.
- In the demo, the model set up a proxy through ChatGPT Sites, downloaded Gemma 3 4B, installed Ollama, and ran inference in about 14 minutes.
- The benchmark screenshot shows 8.46 tokens/s generation and a 20.9s cold request.
The main takeaway is that paid ChatGPT Work users may have access to a remote machine that is much more capable than many people realize.
Related event: ChatGPT Work Offers 15GB Remote VM to Paid Users(3 posts)→
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11