YanoljaNEXT-Rosetta-12B-2510
yanolja's YanoljaNEXT-Rosetta-12B-2510 packs 12 billion parameters into a chat model. YanoljaNEXT-Rosetta-12B-2510 is an open-weights chat model with roughly 12 billion parameters.
by yanolja · 12B parameters
Best for
Ways to use YanoljaNEXT-Rosetta-12B-2510 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your yanolja API key. osFoundry discovers YanoljaNEXT-Rosetta-12B-2510 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
YanoljaNEXT-Rosetta-12B-2510 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 YanoljaNEXT-Rosetta-12B-2510
YanoljaNEXT-Rosetta-12B-2510 runs on a single 16GB consumer GPU (~8 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~29 GB).
YanoljaNEXT-Rosetta-12B-2510 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about YanoljaNEXT-Rosetta-12B-2510
Is YanoljaNEXT-Rosetta-12B-2510 free to use?
YanoljaNEXT-Rosetta-12B-2510 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 YanoljaNEXT-Rosetta-12B-2510 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 YanoljaNEXT-Rosetta-12B-2510 need?
Approximately 8 GB at Q4 quantisation, or 29 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run YanoljaNEXT-Rosetta-12B-2510 locally?
Yes. YanoljaNEXT-Rosetta-12B-2510 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is YanoljaNEXT-Rosetta-12B-2510 best at?
YanoljaNEXT-Rosetta-12B-2510 is well-suited to translation.
How do I use YanoljaNEXT-Rosetta-12B-2510 in osFoundry?
Paste your yanolja API key in the key dialog (or deploy the open weights for self-hostable models), assign YanoljaNEXT-Rosetta-12B-2510 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by yanolja on October 9, 2025. Source: https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-12B-2510