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 software performance optimization
- Recent Ecosystem Updates: The release of Qwen 3.8-Max highlights the trend of high-capability models with open-source variants (e.g., Qwen 3.8-27B) for local deployment and autonomous coding tasks Qwen 3.8-Max: Autonomous Coding, Debugging, and Open-Source Qwen 3.8-27B