olmo3-7b-DPO-ours_wo_r
olmo3-7b-DPO-ours_wo_r is a 7 billion parameter chat model from sma1-rmarud, released May 1, 2026. olmo3-7b-DPO-ours_wo_r is an open-weights chat model with roughly 7 billion parameters.
by sma1-rmarud · 7B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use olmo3-7b-DPO-ours_wo_r in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your sma1-rmarud API key. osFoundry discovers olmo3-7b-DPO-ours_wo_r 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
olmo3-7b-DPO-ours_wo_r 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 olmo3-7b-DPO-ours_wo_r
olmo3-7b-DPO-ours_wo_r runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~17 GB).
olmo3-7b-DPO-ours_wo_r vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about olmo3-7b-DPO-ours_wo_r
Is olmo3-7b-DPO-ours_wo_r free to use?
olmo3-7b-DPO-ours_wo_r 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 olmo3-7b-DPO-ours_wo_r 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 olmo3-7b-DPO-ours_wo_r need?
Approximately 5 GB at Q4 quantisation, or 17 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run olmo3-7b-DPO-ours_wo_r locally?
Yes. olmo3-7b-DPO-ours_wo_r is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is olmo3-7b-DPO-ours_wo_r best at?
olmo3-7b-DPO-ours_wo_r is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use olmo3-7b-DPO-ours_wo_r in osFoundry?
Paste your sma1-rmarud API key in the key dialog (or deploy the open weights for self-hostable models), assign olmo3-7b-DPO-ours_wo_r to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by sma1-rmarud on May 1, 2026. Source: https://huggingface.co/sma1-rmarud/olmo3-7b-DPO-ours_wo_r