Understand open weights
Architecture, weights, and runtime
Separate the model design, learned parameters, tokenizer, and inference software that cooperate during a local response.
A local AI application has several parts. Calling all of them “the model” hides useful differences.
The architecture describes the model shape: its layers, attention mechanism, dimensions, and how values move through the network.
The weights fill that architecture with learned numbers.
The tokenizer converts text into token IDs the model understands, then converts generated IDs back into text.
The runtime loads these files and performs the calculations. Ollama, llama.cpp, MLX LM, and Transformers are examples of runtimes or runtime toolkits.
A model also needs configuration and a chat template. The template turns conversation roles into the exact token pattern used during instruction training. A wrong template can make good weights behave badly.
The complete path is:
prompt -> chat template -> tokenizer -> architecture + weights -> token IDs -> textThis explains why one model file does not run inside every application. The runtime must support the architecture, file format, tokenizer, and features you need.
Lesson completed