Digitorn
Digitorn
All terms
Models & inference

Open-weight model

A model whose weights are publicly downloadable, runnable on your own hardware via Ollama, vLLM, or similar.

also known as: open source model, self-hostable LLM
In depth

Open-weight models (Llama, Qwen, DeepSeek, Mistral) ship the actual weights so you can run inference on your own GPU. Quality lags frontier models for the hardest tasks but closes monthly. The right choice when data residency matters, when you want zero per-token cost, or when you need fully offline operation. Pair with Ollama for laptop-scale work, vLLM for production throughput.

Related concepts
Newsletter

Get the next post in your inbox.

Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.

One-click unsubscribe. We never share your address. Powered by our own infrastructure, not a tracker.

More in Models & inference

Context window/glossary/context-windowFrontier model/glossary/frontier-modelInference/glossary/inferenceLLM/glossary/llmStreaming/glossary/streamingTemperature/glossary/temperature