open-weight model

A machine learning model whose weights (learned parameters) are publicly accessible, enabling local deployment, auditing, and customization without proprietary restrictions. Differs from closed-weight models (e.g., most commercial LLMs) where weights are withheld.

Key characteristics:

• Weights available for download (e.g., via public repositories)
• May not include full training code/data (only weights)
• Enables offline use, customization, and transparency
• Often distributed under permissive licenses

Recent example:

• OpenAI’s gpt-oss-20b and gpt-oss-120b variants (as detailed in Jeredblu running LLM locally)
• Allows local inference without API dependencies

Related concepts:

• large-language-model (LLM)
• open-source
• Model Quantization (common for local deployment)
• hugging-face (platform for sharing open-weight models)

Backlink: 2026 04 14 Jeredblu running LLM locally

Source Notes

• 2026-04-23: Engine Survival: The Critical Role of Oil Pressure and Warning Lights
• 2026-04-27: [[concepts/gemma-4|Google Gemma 4: Open-Weight AI for Local, Private Execution]]