RO-SEC-14B-Final-Merged
Released by spiraljng in 2026, RO-SEC-14B-Final-Merged is a 14 billion parameter chat model. RO-SEC-14B-Final-Merged is an open-weights chat model with roughly 14 billion parameters.
by spiraljng · 14B parameters
Best for
Ways to use RO-SEC-14B-Final-Merged in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your spiraljng API key. osFoundry discovers RO-SEC-14B-Final-Merged automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
RO-SEC-14B-Final-Merged is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run RO-SEC-14B-Final-Merged
RO-SEC-14B-Final-Merged runs on a single 16GB consumer GPU (~9 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~34 GB).
RO-SEC-14B-Final-Merged vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about RO-SEC-14B-Final-Merged
Is RO-SEC-14B-Final-Merged free to use?
RO-SEC-14B-Final-Merged is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use RO-SEC-14B-Final-Merged commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does RO-SEC-14B-Final-Merged need?
Approximately 9 GB at Q4 quantisation, or 34 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run RO-SEC-14B-Final-Merged locally?
Yes. RO-SEC-14B-Final-Merged is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is RO-SEC-14B-Final-Merged best at?
RO-SEC-14B-Final-Merged is well-suited to text generation.
How do I use RO-SEC-14B-Final-Merged in osFoundry?
Paste your spiraljng API key in the key dialog (or deploy the open weights for self-hostable models), assign RO-SEC-14B-Final-Merged to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by spiraljng on April 23, 2026. Source: https://huggingface.co/spiraljng/RO-SEC-14B-Final-Merged