sarvam-105b
Built by sarvamai, sarvam-105b is a 105 billion parameter chat model. sarvam-105b is an open-weights chat model with roughly 105 billion parameters.
by sarvamai · 105B parameters
Best for
Ways to use sarvam-105b in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your sarvamai API key. osFoundry discovers sarvam-105b 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-105b 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-105b
sarvam-105b runs on a single A100 80GB or H100 80GB at Q4 quantisation (~63 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~252 GB).
sarvam-105b vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about sarvam-105b
Is sarvam-105b free to use?
sarvam-105b 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-105b 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-105b need?
Approximately 63 GB at Q4 quantisation, or 252 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run sarvam-105b locally?
Yes. sarvam-105b is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is sarvam-105b best at?
sarvam-105b is well-suited to text generation.
How do I use sarvam-105b in osFoundry?
Paste your sarvamai API key in the key dialog (or deploy the open weights for self-hostable models), assign sarvam-105b 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-105b