Stockmark-2-100B-Instruct
stockmark's Stockmark-2-100B-Instruct packs 100 billion parameters into a chat model. Stockmark-2-100B-Instruct is an open-weights chat model with roughly 100 billion parameters.
by stockmark · 100B parameters
Best for
Ways to use Stockmark-2-100B-Instruct in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your stockmark API key. osFoundry discovers Stockmark-2-100B-Instruct 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
Stockmark-2-100B-Instruct 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 Stockmark-2-100B-Instruct
Stockmark-2-100B-Instruct runs on a single A100 80GB or H100 80GB at Q4 quantisation (~60 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~240 GB).
Stockmark-2-100B-Instruct vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Stockmark-2-100B-Instruct
Is Stockmark-2-100B-Instruct free to use?
Stockmark-2-100B-Instruct 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 Stockmark-2-100B-Instruct 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 Stockmark-2-100B-Instruct need?
Approximately 60 GB at Q4 quantisation, or 240 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Stockmark-2-100B-Instruct locally?
Yes. Stockmark-2-100B-Instruct is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Stockmark-2-100B-Instruct best at?
Stockmark-2-100B-Instruct is well-suited to text generation.
How do I use Stockmark-2-100B-Instruct in osFoundry?
Paste your stockmark API key in the key dialog (or deploy the open weights for self-hostable models), assign Stockmark-2-100B-Instruct to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by stockmark on July 8, 2025. Source: https://huggingface.co/stockmark/Stockmark-2-100B-Instruct