Rth-lm-25b
RthItalia's Rth-lm-25b packs 25 billion parameters into a chat model. Rth-lm-25b is an open-weights chat model with roughly 25 billion parameters.
by RthItalia · 25B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Rth-lm-25b in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your RthItalia API key. osFoundry discovers Rth-lm-25b 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
Rth-lm-25b 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 Rth-lm-25b
Rth-lm-25b runs on a single 16GB consumer GPU (~15 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~60 GB).
Rth-lm-25b vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Rth-lm-25b
Is Rth-lm-25b free to use?
Rth-lm-25b 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 Rth-lm-25b 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 Rth-lm-25b need?
Approximately 15 GB at Q4 quantisation, or 60 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Rth-lm-25b locally?
Yes. Rth-lm-25b is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Rth-lm-25b best at?
Rth-lm-25b is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Rth-lm-25b in osFoundry?
Paste your RthItalia API key in the key dialog (or deploy the open weights for self-hostable models), assign Rth-lm-25b to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by RthItalia on February 12, 2026. Source: https://huggingface.co/RthItalia/Rth-lm-25b