Skywork-Reward-V2-Llama-3.1-8B-40M
Released by Skywork in 2025, Skywork-Reward-V2-Llama-3.1-8B-40M is a 8 billion parameter chat model. Skywork-Reward-V2-Llama-3.1-8B-40M is an open-weights chat model with roughly 8 billion parameters.
by Skywork · 8B parameters
Best for
Ways to use Skywork-Reward-V2-Llama-3.1-8B-40M in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Skywork API key. osFoundry discovers Skywork-Reward-V2-Llama-3.1-8B-40M 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
Skywork-Reward-V2-Llama-3.1-8B-40M 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 Skywork-Reward-V2-Llama-3.1-8B-40M
Skywork-Reward-V2-Llama-3.1-8B-40M 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 (~20 GB).
Skywork-Reward-V2-Llama-3.1-8B-40M vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Skywork-Reward-V2-Llama-3.1-8B-40M
Is Skywork-Reward-V2-Llama-3.1-8B-40M free to use?
Skywork-Reward-V2-Llama-3.1-8B-40M 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 Skywork-Reward-V2-Llama-3.1-8B-40M 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 Skywork-Reward-V2-Llama-3.1-8B-40M need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run Skywork-Reward-V2-Llama-3.1-8B-40M locally?
Yes. Skywork-Reward-V2-Llama-3.1-8B-40M is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Skywork-Reward-V2-Llama-3.1-8B-40M best at?
Skywork-Reward-V2-Llama-3.1-8B-40M is well-suited to text classification.
How do I use Skywork-Reward-V2-Llama-3.1-8B-40M in osFoundry?
Paste your Skywork API key in the key dialog (or deploy the open weights for self-hostable models), assign Skywork-Reward-V2-Llama-3.1-8B-40M to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Skywork on June 26, 2025. Source: https://huggingface.co/Skywork/Skywork-Reward-V2-Llama-3.1-8B-40M