Build LLM

// Selecting best model for RTX 5080 · 16 GB VRAM

GPU busy — another job is running. You are queued.
Initialising…
0%
1
Select Model
// Choose the AI model — best available is auto-selected
PENDING
2
Pull Model to GPU
// Downloading weights — stored locally after first pull
Waiting...
PENDING
3
Extract Q&A Chunks
// LLM breaks each document into granular question-answer pairs
Waiting...
PENDING
4
Generate Embeddings
// nomic-embed-text converts each chunk to a semantic vector
Waiting...
PENDING
5
Ingest & Ready
// Bake knowledge base into a custom model for direct Q&A
PENDING
Loading...