SAGE-MM-Qwen3-VL-8B-SFT_RL
SAGE-MM-Qwen3-VL-8B-SFT_RL (allenai, 2025) is a 8 billion parameter video-generation model. SAGE-MM-Qwen3-VL-8B-SFT_RL is an open-weights video model with roughly 8 billion parameters.
by allenai · 8B parameters
Best for
Ways to use SAGE-MM-Qwen3-VL-8B-SFT_RL in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your allenai API key. osFoundry discovers SAGE-MM-Qwen3-VL-8B-SFT_RL 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
SAGE-MM-Qwen3-VL-8B-SFT_RL 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 SAGE-MM-Qwen3-VL-8B-SFT_RL
SAGE-MM-Qwen3-VL-8B-SFT_RL 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).
SAGE-MM-Qwen3-VL-8B-SFT_RL vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about SAGE-MM-Qwen3-VL-8B-SFT_RL
Is SAGE-MM-Qwen3-VL-8B-SFT_RL free to use?
SAGE-MM-Qwen3-VL-8B-SFT_RL 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 SAGE-MM-Qwen3-VL-8B-SFT_RL 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 SAGE-MM-Qwen3-VL-8B-SFT_RL need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run SAGE-MM-Qwen3-VL-8B-SFT_RL locally?
Yes. SAGE-MM-Qwen3-VL-8B-SFT_RL is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is SAGE-MM-Qwen3-VL-8B-SFT_RL best at?
SAGE-MM-Qwen3-VL-8B-SFT_RL is well-suited to video text to text.
How do I use SAGE-MM-Qwen3-VL-8B-SFT_RL in osFoundry?
Paste your allenai API key in the key dialog (or deploy the open weights for self-hostable models), assign SAGE-MM-Qwen3-VL-8B-SFT_RL to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by allenai on November 23, 2025. Source: https://huggingface.co/allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL