sdar-4b-mrp-3lyr
sdar-4b-mrp-3lyr (heavyball, 2026) is a 4 billion parameter chat model. sdar-4b-mrp-3lyr is an open-weights chat model with roughly 4 billion parameters.
by heavyball · 4B parameters
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use sdar-4b-mrp-3lyr in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your heavyball API key. osFoundry discovers sdar-4b-mrp-3lyr 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
sdar-4b-mrp-3lyr 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 sdar-4b-mrp-3lyr
sdar-4b-mrp-3lyr runs on a single 16GB consumer GPU (~3 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~10 GB).
sdar-4b-mrp-3lyr vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about sdar-4b-mrp-3lyr
Is sdar-4b-mrp-3lyr free to use?
sdar-4b-mrp-3lyr 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 sdar-4b-mrp-3lyr 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 sdar-4b-mrp-3lyr need?
Approximately 3 GB at Q4 quantisation, or 10 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run sdar-4b-mrp-3lyr locally?
Yes. sdar-4b-mrp-3lyr is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is sdar-4b-mrp-3lyr best at?
sdar-4b-mrp-3lyr is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use sdar-4b-mrp-3lyr in osFoundry?
Paste your heavyball API key in the key dialog (or deploy the open weights for self-hostable models), assign sdar-4b-mrp-3lyr to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by heavyball on May 9, 2026. Source: https://huggingface.co/heavyball/sdar-4b-mrp-3lyr