VRAM ≠
model file size
model file size
Knowledge for a brighter tomorrow
Understand
what’s next.
Practical AI knowledge, reproducible tests and implementation-focused tutorials.
Learn
Understand technologyBuild
Use it in practiceTest
See how it performsStart with something practical
Understand → plan → run → measure
VRAM + RAM
→ fit?
→ fit?
Plan
Local Model Fit Checker
Check whether a configuration is likely to fit your hardware before loading it.
Check a model →$ ollama run model
>>> ready_
>>> ready_
Run
Run a model with Ollama
Go from an installed runtime to repeatable local inference.
Follow tutorial →3 models
12 runs
3 GB VRAM
12 runs
3 GB VRAM
Measure
When models outgrow VRAM
Compare runtime residency and warm generation throughput in LAB #005.
Open test →DOCEO LAB
Measured.
Reproducible.
Scoped.
Real environments, exact configurations, repeatable commands and explicit limitations.
Explore the Lab →How E—DOCEO works
No mystery numbers.
Documentation explains expected behavior. Tutorials reproduce workflows. Lab records publish what we actually measured and where those measurements stop being generalizable.