If we haven't run it,
we don't write it.

Model fine-tuning, inference servers, workflow automation — hands-on GPU cloud notes from experiments we ran ourselves on gcube. Every benchmark and code sample is reproducible.

gcube Lab

Hands-on notes · Updated weekly

featured

Building a RAG chatbot on gcube docs with an RTX 5090

We embedded the official gcube docs with BGE-M3, indexed them in Chroma, and connected them to Qwen2.5-7B served with vLLM. The entire pipeline runs in a notebook on a single RTX 5090, with no external APIs.

2026-07-16▸ RTX 5090~ 40 min

Fine-tuning Llama 3.1 on an RTX 5090

Hands-on notes from fine-tuning Llama 3.1 8B on a Korean dataset with Unsloth in gcube’s RTX 5090 environment.

2026-06-25▸ RTX 5090~ 40 min

Fine-tuningLLMGPU

If we haven't run it,we don't write it.

Sovereign AI Stack 2026

Building a RAG chatbot on gcube docs with an RTX 5090

Fine-tuning Llama 3.1 on an RTX 5090

If we haven't run it,
we don't write it.