d3 decision models (local)
Routing support tickets, triaging documents and yes/no or score checks on text, structured data or images, with probabilities instead of a written answer.
Run it locally
ollama run d3- Ollama tag
- d3 (4B default; also d3:2b, d3:9b, d3:27b)
- LM Studio name
- Not in the LM Studio catalog yet
- Download size by quantization
- 2B 3.1 GB; 4B 5.6 GB; 9B 10 GB; 27B 29 GB
- License
- Apache 2.0
Memory needed is roughly the download size plus 2 to 4 GB for context. See how to run AI locally.
Specs and prices checked 2026-10-23 against the official page.
Used in these setups
Related skills and personas
Agent skills and bot personas that pair well with d3 decision models (local).
GitLab MCP Server
GitLab's official MCP server: merge requests, work items, pipelines, code search and Duo Agent Platform flows, under your own GitLab permissions.
Sentry Error Monitoring MCP Server
Retrieve real-time production exception stack traces, error frequency, and breadcrumbs.
Slack Collaboration MCP Server
Query team Slack channels, search conversation history, and post structured incident updates.
Application Security Code Review Setup
Systematic OWASP Top 10 code audit, dependency vulnerability scanning, and secret leak detection.
The Cloud & Edge SRE
Five nines uptime, automated rollback pipelines, low-latency edge deployment, and telemetry.
The Checklist Surgeon
Turns a messy, error-prone process into a short checklist people will actually use, with clear pause points.
Want tested skills and personas installed in one command? See the AI Loadout packs, from $9.