sarvam-105b-fp8
Built by sarvamai, sarvam-105b-fp8 is a 105 billion parameter chat model. sarvam-105b-fp8 is an open-weights chat model with roughly 105 billion parameters.
by sarvamai · 105B parameters
Best for
Ways to use sarvam-105b-fp8 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your sarvamai API key. osFoundry discovers sarvam-105b-fp8 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-fp8 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-fp8
sarvam-105b-fp8 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-fp8 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-fp8
Is sarvam-105b-fp8 free to use?
sarvam-105b-fp8 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-fp8 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-fp8 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-fp8 locally?
Yes. sarvam-105b-fp8 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is sarvam-105b-fp8 best at?
sarvam-105b-fp8 is well-suited to text generation.
How do I use sarvam-105b-fp8 in osFoundry?
Paste your sarvamai API key in the key dialog (or deploy the open weights for self-hostable models), assign sarvam-105b-fp8 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 25, 2026. Source: https://huggingface.co/sarvamai/sarvam-105b-fp8