People who want to set application-specific system prompts around a locally run assistant.
The model documentation identifies an instruction-tuned Llama 3.1 8B release for coding, math and general use.
Control over the system prompt is not a claim that outputs are safe, accurate, lawful or appropriate for every use. No unrestricted-content filter or adult category is added. Function calling needs application support, and the 4.9GB package is not a RAM minimum.
No hosted subscription or token fee for local inference within the license’s permitted uses. Hardware, electricity and setup are separate. Llama 3.1 Community License Agreement and associated obligations apply.
Install a current compatible Ollama version, review the exact model license, then run: ollama run dolphin3:8b. API means the local runtime endpoint, not a hosted service included with the weights.
Tags
© Chagto 2026. All rights reserved