#separator:tab
#html:true
#tags:open-models-quiz
#columns:Front Back
You turn off wi-fi, and the model in LM Studio still answers. What follows from this?
- The whole model is stored on the laptop as a file and is computed by its processor or graphics card.
- LM Studio caches earlier answers from the internet and replays them while offline.
- The model answers from a small database of texts that was installed with LM Studio.
- The model sends the questions once the connection is back and shows provisional answers until then.
- The whole model is stored on the laptop as a file and is computed by its processor or graphics card.
Correct: everything the model can do lies in the file with its parameters; nothing else is needed to answer.
A model has 8 billion parameters, each stored with 4 bits. About how big is the file?
- 4 GB
- 8 GB
- 32 GB
- 16 GB
- 4 GB
Correct: 8 billion times 4 bits is 32 billion bits, which is 4 billion bytes.
On the same laptop, Gemma 3 4B answers noticeably more slowly than Gemma 3 1B. Why?
- Every token passes through all parameters, and the 4B model has four times as many.
- The larger model searches a larger database of texts for every answer.
- The larger model writes longer answers because it knows more.
- The larger model checks every answer on the internet before showing it.
- Every token passes through all parameters, and the 4B model has four times as many.
Correct: more numbers per token mean more computation per token and therefore fewer tokens per second.
Which statements about open models are correct?
- Their weights can be downloaded and run on your own hardware.
- Their training data is always published along with the weights.
- They can be adapted, for example fine-tuned on your own data.
- They may come with licences that restrict some uses.
- They cannot be used inside an agent.
- Their weights can be downloaded and run on your own hardware.
Correct: this is exactly what makes a model open. - They can be adapted, for example fine-tuned on your own data.
Correct: whoever has the weights can change them further. - They may come with licences that restrict some uses.
Correct: open does not mean without conditions; some licences limit commercial use, for example.
In which situation is a local open model the most sensible choice?
- A veterinary practice wants to summarise treatment notes that must not leave the practice.
- A student wants the best possible answer to a difficult research question on a slow laptop.
- A start-up wants to try out many different models quickly without buying hardware.
- A marketing team needs current competitor prices from the web.
- A veterinary practice wants to summarise treatment notes that must not leave the practice.
Correct: when the data must not leave the building, a local model is often the only way.
What does it mean to quantize a model?
- Storing the parameters with fewer bits, which makes the file smaller and costs a little quality.
- Removing rarely used words from the vocabulary so that the model gets faster.
- Splitting the model into parts that run on several computers.
- Training the model a second time on less data.
- Storing the parameters with fewer bits, which makes the file smaller and costs a little quality.
Correct: the numbers are rounded so that the model fits into memory.