Model Weights
Parameters learned during training that define a model’s behavior. Stored in files (e.g., .bin, .pt) and loaded for inference. Size directly impacts computational requirements (e.g., 20B parameters ≈ 40GB storage).
Key Characteristics
- Open-weight models (e.g.,
[[concepts/gpt-oss-20b|gpt-oss-20b]]) publicly share weights while keeping training code proprietary - Local deployment requires downloading weights (e.g., via Hugging Face Hub)
- Inference executes using weights without cloud dependency; loading/running involves inference engines, memory-mapping, and performance optimization rather than simple file execution (see Kimi K3: Moonshot AI’s Open-Weight Breakthrough in Coding and Web Development)
- Recent Developments: Moonshot AI released Kimi K3, an “Open Frontier Intelligence” model highlighting advancements in coding and web development capabilities within the open-weight ecosystem