Open Weights: Run Your Own AI
Open-weight models let anyone download a trained AI and run it on their own hardware, but what does that really mean?
- Technology
- Adults
- Medium
- Educational
- 13 questions
- about 7 min
- Feedback after each question
Against each other
For kids and playful souls
See the questions
Without the right answers, so they're still a surprise when you play.
Question 1
In an AI model, what are the "weights"?
- The program code that defines how the model runs
- The amount of text the model can read at once
- The full dataset the model was trained on
- The learned numbers that set the model's behavior
Question 2
What is the common name for shrinking a model by storing its weights with fewer bits, such as 4-bit?
- Fine-tuning
- Quantization
- Low-rank adaptation
- Distillation scaling
Question 3
A company releases a model's weights but not its training data or training code. How is it best described?
- Fully open source, since anyone can download it
- Free for any commercial use, by definition
- Open-weight, but not fully open source
- Open source, because weights count as source code
Question 4
Why do many hospitals and law firms like self-hosted models?
- Prompts are still logged by the model maker
- They need constant internet to generate replies
- Bigger models are always more accurate for them
- Sensitive data can stay on their own machines
Question 5
A 7-billion-parameter model is stored at 16 bits (2 bytes) per weight. Roughly how much memory do the weights need?
- About 3.5 GB
- About 7 GB
- About 14 GB
- About 56 GB
Question 6
You quantize that same 7B model from 16-bit to 4-bit. About how big are the weights now?
- About 3.5 GB
- About 14 GB
- About 7 GB
- About 28 GB
Question 7
A startup wants to sell an app built on an open-weight model. What should it check first?
- Nothing, since open weights allow any commercial use
- Only whether the model passed its safety tests
- The model's license terms for commercial use
- Whether the training data is included in the download
Question 8
You want a model to answer in your company's style, with one GPU and little time. Which approach fits best?
- Retrain the whole model from scratch on your text
- Fine-tune all billions of weights at full precision
- Train a LoRA adapter on examples of your style
- Switch to the largest model you can download
Question 9
On a flight with no Wi-Fi, can a model already downloaded to your laptop still answer questions?
- No, it must contact its maker's servers to think
- Yes, because it runs fully on the laptop
- No, it only stores the questions until you reconnect
- Only if the laptop has no graphics chip at all
Question 10
A 13B model runs slowly on a laptop, but quickly on a desktop with a big GPU. What mainly explains it?
- The CPU and GPU are equally fast at this work
- The desktop has a longer context window built in
- The 13B model is smarter on the desktop
- GPU memory bandwidth and parallel math speed
Question 11
A small 8B model beats an older 70B model on many tests. What does this best show?
- Training data and methods matter, not only size
- The tests must have measured context length only
- Parameter count is all that decides quality
- Smaller models always store more training data
Question 12
Which claim about open-weight models holds up best?
- They are safe by default since anyone can inspect them
- They let outsiders study and adapt models, but safeguards can be removed
- They show their full training data to anyone who downloads them
- They send usage data back to improve the original model
Question 13
A clinic wants a private chatbot that answers from its own policy files, on one 24 GB GPU. Which plan would work?
- Run a 70B model at 16-bit and paste all files in
- Pretrain a new model from scratch on the policy files
- Use a hosted chatbot that keeps prompts on its servers
- Run a 4-bit 8B model locally with document retrieval






