sarvam-30b
Released by sarvamai in 2026, sarvam-30b is a 30 billion parameter chat model. sarvam-30b is an open-weights chat model with roughly 30 billion parameters.
by sarvamai · 30B parameters
Best for
Ways to use sarvam-30b in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your sarvamai API key. osFoundry discovers sarvam-30b 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
sarvam-30b 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 sarvam-30b
sarvam-30b runs on a 24GB consumer or workstation GPU (~18 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~72 GB).
sarvam-30b vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about sarvam-30b
Is sarvam-30b free to use?
sarvam-30b 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 sarvam-30b 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 sarvam-30b need?
Approximately 18 GB at Q4 quantisation, or 72 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run sarvam-30b locally?
Yes. sarvam-30b is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is sarvam-30b best at?
sarvam-30b is well-suited to text generation.
How do I use sarvam-30b in osFoundry?
Paste your sarvamai API key in the key dialog (or deploy the open weights for self-hostable models), assign sarvam-30b to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by sarvamai on March 3, 2026. Source: https://huggingface.co/sarvamai/sarvam-30b